© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 21-LLAMASCOPE-RES-32K
    11. 12150
    Prev
    Next
    INDEX
    Explanations

    references to an organization or entity involved in oversight or control, particularly in a regulatory or investigative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ances
    -0.18
    antino
    -0.16
    antly
    -0.15
    ELY
    -0.15
    aos
    -0.15
    mae
    -0.15
    à¥įवत
    -0.15
    ÛĮد
    -0.14
    unce
    -0.14
    fern
    -0.14
    POSITIVE LOGITS
     provoc
    0.29
    ing
    0.19
     agents
    0.19
    .Agent
    0.19
    -agent
    0.19
    -Agent
    0.18
    gy
    0.17
     Agents
    0.17
     agent
    0.16
    415
    0.16
    Activations Density 0.025%

    No Known Activations