Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 16474
    Prev
    Next
    INDEX
    Explanations

    keyword identifiers and object attributes in programming contexts

    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
    ведиÑĤе
    -0.10
     latter
    -0.09
    plevel
    -0.09
    bidden
    -0.08
    longleftrightarrow
    -0.08
    rastructure
    -0.08
    aphore
    -0.08
    thern
    -0.08
    anity
    -0.08
    keit
    -0.08
    POSITIVE LOGITS
    orem
    0.07
    odore
    0.07
    wards
    0.06
    /-
    0.06
    scriptions
    0.06
    ãĤ¶ãĤ¤ãĥ³
    0.06
    ovich
    0.06
    raries
    0.06
    Ìģ
    0.06
    enticator
    0.06
    Activations Density 0.314%

    No Known Activations