© 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. 76790
    Prev
    Next
    INDEX
    Explanations

    phrases related to the provision of resources or assistance

    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
    abant
    -0.08
    enties
    -0.07
    shima
    -0.07
    ulfilled
    -0.07
    reature
    -0.07
    okable
    -0.07
    acos
    -0.07
    esso
    -0.06
    iminal
    -0.06
    izontal
    -0.06
    POSITIVE LOGITS
     opportunities
    0.09
     opportunity
    0.09
    ims
    0.07
    ono
    0.07
     hol
    0.06
    weg
    0.06
     oportun
    0.06
    burg
    0.06
    Issuer
    0.06
     Opportunities
    0.06
    Activations Density 0.025%

    No Known Activations