© 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. 87806
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their relationships

    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
    rench
    -0.07
    dera
    -0.07
    ková
    -0.06
    emsp
    -0.06
    avors
    -0.06
    rost
    -0.06
    reib
    -0.05
    Ŀ
    -0.05
    /lists
    -0.05
     mode
    -0.05
    POSITIVE LOGITS
     Jr
    0.10
    خاÙĨ
    0.07
    ofday
    0.07
    addock
    0.06
    θα
    0.06
    062
    0.06
     brag
    0.06
     ragaz
    0.06
    .install
    0.06
    imuth
    0.06
    Activations Density 0.010%

    No Known Activations