© 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. 61206
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Add" and its variations, indicating a focus on adding items or actions

    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
    orum
    -0.07
    dling
    -0.06
    лим
    -0.06
    "crypto
    -0.06
    ear
    -0.06
    ój
    -0.06
     verst
    -0.06
    transfer
    -0.05
     Colonial
    -0.05
    arrant
    -0.05
    POSITIVE LOGITS
    resse
    0.08
    ITIONAL
    0.08
    ancel
    0.07
    .Invariant
    0.07
    endum
    0.07
    éri
    0.07
    ÃŃrk
    0.07
    ãĥ³ãĤ¬
    0.07
    ional
    0.07
    agnost
    0.07
    Activations Density 0.009%

    No Known Activations