Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119228
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contr
    -0.06
    hof
    -0.06
    ardin
    -0.06
     charge
    -0.06
     Charge
    -0.06
    abay
    -0.06
    hower
    -0.06
    ung
    -0.06
    rab
    -0.06
    manifest
    -0.06
    POSITIVE LOGITS
    REFERRED
    0.08
    -urlencoded
    0.08
    StateChanged
    0.07
    าà¸ĺ
    0.07
    jte
    0.07
    brid
    0.07
    enever
    0.07
    umeric
    0.07
    éĢĢ
    0.07
    iaux
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.