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. 77175
    Prev
    Next
    INDEX
    Explanations

    terms related to education and skill level

    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
    alu
    -0.08
    oran
    -0.07
    alta
    -0.07
    allas
    -0.07
    amespace
    -0.07
    loh
    -0.07
    fall
    -0.07
    asu
    -0.07
    _configure
    -0.07
    olle
    -0.07
    POSITIVE LOGITS
    /lic
    0.07
    nes
    0.07
    ness
    0.07
     persons
    0.07
     enough
    0.07
    NESS
    0.06
    ?url
    0.06
    ãĤ¦ãĥĪ
    0.06
    ÑĪÑĮ
    0.06
    thood
    0.06
    Activations Density 0.012%

    No Known Activations