© 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. 77471
    Prev
    Next
    INDEX
    Explanations

    nouns related to written content or literary works

    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
    awa
    -0.06
    ified
    -0.06
    520
    -0.06
     hyp
    -0.06
    amik
    -0.06
    ometr
    -0.06
    Snapshot
    -0.06
     equ
    -0.05
     end
    -0.05
    tas
    -0.05
    POSITIVE LOGITS
     hopefully
    0.08
    hopefully
    0.07
    prm
    0.07
    aternion
    0.07
    .scalablytyped
    0.07
     showc
    0.07
    ettings
    0.07
     nhằm
    0.07
    symbols
    0.07
    porno
    0.07
    Activations Density 0.024%

    No Known Activations