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. 87524
    Prev
    Next
    INDEX
    Explanations

    details related to customer service experiences and employment situations

    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
     or
    -0.07
    estre
    -0.07
     perhaps
    -0.06
    ledon
    -0.06
    digit
    -0.06
    ieder
    -0.06
     HERE
    -0.06
    lisi
    -0.06
    ostel
    -0.06
    OrFail
    -0.06
    POSITIVE LOGITS
     millenn
    0.07
    .PropTypes
    0.07
    ?(:
    0.07
    PointerException
    0.06
     AppRoutingModule
    0.06
    -lnd
    0.06
    ÏĦιÏĥ
    0.06
    ÙĦÙħÙĩ
    0.06
    IIIK
    0.06
    ~-~-
    0.06
    Activations Density 0.002%

    No Known Activations