© 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. 3440
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses involving subject-verb relationships, often highlighting qualities or characteristics

    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
    .scalablytyped
    -0.08
     lÃł
    -0.08
    æĺ¯ä¸ª
    -0.07
    .abstract
    -0.07
    èĬ³
    -0.07
     '<%=
    -0.07
    ÙħاÙĦ
    -0.07
    [".
    -0.07
    .nlm
    -0.07
    (CType
    -0.07
    POSITIVE LOGITS
     with
    0.07
     deserves
    0.07
     yet
    0.07
     deserve
    0.06
    ä¸Ķ
    0.06
    ena
    0.06
     worth
    0.06
     nonetheless
    0.06
    ler
    0.06
     poorly
    0.06
    Activations Density 0.049%

    No Known Activations