© 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. 76794
    Prev
    Next
    INDEX
    Explanations

    HTML title tags

    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
    _NATIVE
    -0.07
    uli
    -0.07
    legg
    -0.07
    AccessException
    -0.06
    enia
    -0.06
    ernity
    -0.06
    stroy
    -0.06
    779
    -0.06
    chant
    -0.06
    elia
    -0.06
    POSITIVE LOGITS
    artin
    0.08
    fish
    0.07
    jets
    0.06
    ाà¤Ĭ
    0.06
     âĵĺ
    0.06
    ipmap
    0.06
    .SQLite
    0.06
     fork
    0.06
    :///
    0.06
    едж
    0.06
    Activations Density 0.000%

    No Known Activations