© 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. 94169
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to dates and statistics

    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
    ime
    -0.06
    ascar
    -0.06
    ention
    -0.06
     trusted
    -0.06
    illet
    -0.06
    aney
    -0.06
    å«
    -0.06
     cong
    -0.05
     force
    -0.05
    iating
    -0.05
    POSITIVE LOGITS
    ETIME
    0.08
    ingly
    0.08
    llen
    0.08
    STYPE
    0.08
    ively
    0.08
    onium
    0.08
    oÅĻ
    0.08
    ture
    0.07
    aged
    0.07
    shade
    0.07
    Activations Density 0.046%

    No Known Activations