© 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. 126308
    Prev
    Next
    INDEX
    Explanations

    words related to essential or necessary concepts

    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
    aurant
    -0.07
    kke
    -0.07
    oice
    -0.07
    overy
    -0.07
    unist
    -0.07
    دÛĮد
    -0.07
    ëĤĺ무
    -0.06
    cep
    -0.06
    incr
    -0.06
    ales
    -0.06
    POSITIVE LOGITS
    entially
    0.10
    linger
    0.07
    y
    0.07
    most
    0.07
    mates
    0.06
    ential
    0.06
    uela
    0.06
    urrect
    0.06
    leine
    0.06
    ikal
    0.06
    Activations Density 0.007%

    No Known Activations