© 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. 16087
    Prev
    Next
    INDEX
    Explanations

    phrases or constructs that indicate a causal relationship or conditions surrounding a situation

    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
    .Obj
    -0.08
    ãĥ¼ãĥ
    -0.07
     اÙĪÙĦÛĮÙĩ
    -0.07
    igor
    -0.07
    rift
    -0.07
    Ø
    -0.07
    ίÏĥ
    -0.07
    anna
    -0.07
    aturity
    -0.07
    tech
    -0.07
    POSITIVE LOGITS
     hopefully
    0.08
     it
    0.07
    inel
    0.07
     they
    0.06
     ultimately
    0.06
     we
    0.06
    -ÑĤо
    0.06
     later
    0.06
    fab
    0.06
    upa
    0.06
    Activations Density 0.019%

    No Known Activations