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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 6687
    Prev
    Next
    INDEX
    Explanations

    topics related to threats, risks, and negative consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardon
    -0.16
    bjerg
    -0.15
    åħ±åIJĮ
    -0.15
    entin
    -0.14
    essen
    -0.14
    èªĮ
    -0.14
    ierge
    -0.14
     tslib
    -0.14
    abcdefghijklmnop
    -0.14
    apl
    -0.14
    POSITIVE LOGITS
    igue
    0.16
     bad
    0.16
    ude
    0.15
     Falk
    0.15
    /authentication
    0.14
     sur
    0.14
    ³
    0.14
    akin
    0.14
    stk
    0.14
    oris
    0.14
    Activations Density 0.323%

    No Known Activations