© 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. 56291
    Prev
    Next
    INDEX
    Explanations

    topics related to evolutionary biology and anatomy

    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
    quential
    -0.07
     Sent
    -0.06
    /stretch
    -0.06
    -self
    -0.06
    abus
    -0.06
    è¾°
    -0.06
    زار
    -0.06
    achten
    -0.06
    uset
    -0.06
    Sent
    -0.06
    POSITIVE LOGITS
     bones
    0.08
     bone
    0.08
     oss
    0.07
    bone
    0.07
    UTTON
    0.07
    426
    0.07
    Bone
    0.07
     Paleo
    0.06
     Bone
    0.06
     bosses
    0.06
    Activations Density 0.007%

    No Known Activations