© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84119
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health support and counseling services

    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
    agon
    -0.07
    agra
    -0.07
    kul
    -0.07
    umb
    -0.07
    ptrdiff
    -0.07
    stro
    -0.07
    ATTR
    -0.07
    iring
    -0.07
    .matcher
    -0.06
    avs
    -0.06
    POSITIVE LOGITS
    @brief
    0.07
     issues
    0.07
     Kore
    0.07
    chn
    0.07
     clients
    0.06
    Ñĥков
    0.06
     Clients
    0.06
     bul
    0.06
     Kraft
    0.06
    bere
    0.06
    Activations Density 0.010%

    No Known Activations