© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 10555
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals named "Car."

    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
    kup
    -0.17
    esor
    -0.15
    yte
    -0.15
    amat
    -0.15
    esser
    -0.15
    tors
    -0.15
    nore
    -0.15
    tics
    -0.15
    urma
    -0.14
    datal
    -0.14
    POSITIVE LOGITS
    rying
    0.35
    oline
    0.31
    leton
    0.31
    olina
    0.30
    ibbean
    0.30
    roll
    0.29
    son
    0.29
    rots
    0.29
    lsen
    0.28
    rot
    0.28
    Activations Density 0.018%

    No Known Activations