© 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. 87366
    Prev
    Next
    INDEX
    Explanations

    statistics related to community concerns or public opinion polls

    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
    Äĩe
    -0.08
    arger
    -0.08
    iom
    -0.08
    stoff
    -0.08
    otas
    -0.07
    ilan
    -0.07
    Reviewer
    -0.07
    arges
    -0.07
    StatusLabel
    -0.07
    umo
    -0.07
    POSITIVE LOGITS
     answers
    0.12
     replies
    0.09
     responses
    0.09
     votes
    0.09
     respondents
    0.09
    answers
    0.08
     answered
    0.08
     Answers
    0.08
    çŃĶæ¡Ī
    0.08
    åĽŀçŃĶ
    0.08
    Activations Density 0.022%

    No Known Activations