© 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. 16735
    Prev
    Next
    INDEX
    Explanations

    instances of the word "interview" and its contextual references

    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
    roupon
    -0.08
    kin
    -0.08
    echa
    -0.07
    ãģªãĤī
    -0.07
    lotte
    -0.07
    ohan
    -0.07
    ẩu
    -0.06
    chai
    -0.06
    chap
    -0.06
    ãĥ¼ãĥ¬
    -0.06
    POSITIVE LOGITS
    afx
    0.07
     with
    0.07
    undy
    0.06
    CRT
    0.06
    rels
    0.06
    Framebuffer
    0.06
     interviewer
    0.06
     Masc
    0.06
    /***
    0.06
    .@
    0.06
    Activations Density 0.005%

    No Known Activations