© 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. 17-LLAMASCOPE-RES-131K
    6. 87761
    Prev
    Next
    INDEX
    Explanations

    terms associated with weight and weight management

    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
     Claw
    -0.07
    undi
    -0.06
    utter
    -0.06
    wal
    -0.06
    Åĵ
    -0.06
    inders
    -0.06
    atör
    -0.06
    istent
    -0.06
    lear
    -0.06
    horn
    -0.06
    POSITIVE LOGITS
    lifting
    0.11
    lessness
    0.09
    (weight
    0.08
    amac
    0.07
    siblings
    0.07
    fully
    0.07
    less
    0.07
    ilda
    0.07
    edList
    0.07
    anchor
    0.07
    Activations Density 0.021%

    No Known Activations