© 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. 61231
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing benefits or opportunities

    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
    /F
    -0.06
    ven
    -0.06
    ilon
    -0.06
    .compiler
    -0.06
    less
    -0.06
    rid
    -0.06
    raz
    -0.06
     weg
    -0.05
    prech
    -0.05
    s
    -0.05
    POSITIVE LOGITS
    Interop
    0.09
    ãĥ¼ãĥĨ
    0.08
    hlen
    0.08
    //{{
    0.08
    atatype
    0.07
    íĬ¹ë³Ħ
    0.07
    trys
    0.07
    bare
    0.07
    htable
    0.07
    hoot
    0.07
    Activations Density 0.004%

    No Known Activations