© 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. 55775
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions to indicate relationships between ideas or phrases

    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
    ãĤ¢ãĥ³
    -0.07
    iris
    -0.06
    راد
    -0.06
    èĬĻ
    -0.06
    rada
    -0.06
    FromBody
    -0.06
    Äĥng
    -0.06
    .vertx
    -0.06
    å±ħ
    -0.06
     Cald
    -0.06
    POSITIVE LOGITS
    okies
    0.06
    å·±
    0.06
    enty
    0.06
    coli
    0.06
    èĪª
    0.06
    earer
    0.06
    agini
    0.06
    okie
    0.06
     completed
    0.05
     interim
    0.05
    Activations Density 0.000%

    No Known Activations