© 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. 31-LLAMASCOPE-RES-32K
    6. 10538
    Prev
    Next
    INDEX
    Explanations

    references to cultural or historical contexts involving race and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otto
    -0.15
    ë§ī
    -0.14
    igate
    -0.14
    donnees
    -0.14
     Kup
    -0.14
    mile
    -0.13
    }.{
    -0.13
    mlin
    -0.13
     Hud
    -0.13
    vn
    -0.13
    POSITIVE LOGITS
     possesses
    0.23
     possessing
    0.20
     possessed
    0.19
     Performs
    0.19
     Perform
    0.18
     coming
    0.18
     Fol
    0.18
     performs
    0.18
     possess
    0.18
    poss
    0.17
    Activations Density 0.004%

    No Known Activations