© 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. 61109
    Prev
    Next
    INDEX
    Explanations

    references to photography and related activities

    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
    pus
    -0.06
    ummies
    -0.06
    aska
    -0.06
    çĽĺ
    -0.06
    oren
    -0.06
     пÑĢоÑģ
    -0.06
    ismic
    -0.06
     cour
    -0.06
    uchos
    -0.06
    ereo
    -0.06
    POSITIVE LOGITS
    ifax
    0.08
     booth
    0.08
     Bride
    0.07
     Output
    0.07
     output
    0.07
    -operator
    0.07
    .Output
    0.07
    Automatic
    0.07
     party
    0.06
     Automatic
    0.06
    Activations Density 0.001%

    No Known Activations