© 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. 76177
    Prev
    Next
    INDEX
    Explanations

    patterns related to indexing and organization of information

    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
    rada
    -0.06
    mons
    -0.06
    agua
    -0.06
    tam
    -0.06
    walker
    -0.06
     gode
    -0.06
    æĿľ
    -0.06
    .getChild
    -0.06
    resa
    -0.06
    ãģŁãĤī
    -0.06
    POSITIVE LOGITS
     based
    0.16
    based
    0.13
    åŁºäºİ
    0.11
     Based
    0.11
    _based
    0.11
     dá»±a
    0.10
    Based
    0.10
     via
    0.10
    -by
    0.10
    _via
    0.10
    Activations Density 0.082%

    No Known Activations