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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 24973
    Prev
    Next
    INDEX
    Explanations

    positive expressions of suggestion or desire for improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omi
    -0.17
    atak
    -0.17
    izards
    -0.15
    apsed
    -0.15
    phis
    -0.15
    CV
    -0.15
    ftype
    -0.15
    iect
    -0.15
     freely
    -0.14
    agma
    -0.14
    POSITIVE LOGITS
     Tattoo
    0.15
    actionDate
    0.15
     Faction
    0.15
    ARED
    0.15
    emente
    0.15
    ares
    0.14
    æģ¯
    0.14
     ëĤ´ëł¤
    0.14
    .pub
    0.14
     Choir
    0.14
    Activations Density 0.072%

    No Known Activations