© 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. 15-LLAMASCOPE-RES-131K
    6. 90309
    Prev
    Next
    INDEX
    Explanations

    elements related to political action and accountability

    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
    ovi
    -0.08
    anken
    -0.08
    loub
    -0.07
    óc
    -0.07
    idata
    -0.07
    ÃŃÅĻ
    -0.07
    dad
    -0.07
    anth
    -0.07
     onDataChange
    -0.07
    itos
    -0.07
    POSITIVE LOGITS
    abant
    0.06
    Ïĥιο
    0.06
    ItemType
    0.06
    Carrier
    0.06
     Cabinet
    0.06
    isme
    0.06
     McGr
    0.06
     Hans
    0.06
     prive
    0.06
     carrier
    0.06
    Activations Density 0.001%

    No Known Activations