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. 82917
    Prev
    Next
    INDEX
    Explanations

    references to measurement or analysis points related to evaluation

    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
    ZO
    -0.07
    owler
    -0.07
    queda
    -0.07
    edor
    -0.07
    fol
    -0.06
    ava
    -0.06
    operands
    -0.06
     skal
    -0.06
    icap
    -0.06
     certain
    -0.06
    POSITIVE LOGITS
    riangle
    0.07
     ê°IJìĤ¬
    0.06
    	freopen
    0.06
    _allocated
    0.06
     redo
    0.06
    ãģĭãģĹ
    0.06
    andard
    0.06
    ensem
    0.06
    леÑĩ
    0.06
     Jensen
    0.06
    Activations Density 0.000%

    No Known Activations