© 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. 17-LLAMASCOPE-RES-131K
    11. 118937
    Prev
    Next
    INDEX
    Explanations

    terms related to geological features and seismic activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     SEQ
    -0.06
     subsequ
    -0.06
    uges
    -0.05
    ouver
    -0.05
     Ap
    -0.05
     dign
    -0.05
    ofs
    -0.05
     Attachment
    -0.05
    Continue
    -0.05
    ิว
    -0.05
    POSITIVE LOGITS
     Earth
    0.09
    Earth
    0.08
    agma
    0.08
     press
    0.08
     коÑĢа
    0.07
    mant
    0.07
    ervoir
    0.07
     pressures
    0.07
     Kimber
    0.07
     è±
    0.07
    Activations Density 0.021%

    No Known Activations