© 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. 55818
    Prev
    Next
    INDEX
    Explanations

    references to dogs and cats, especially in the context of their health conditions

    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
    zie
    -0.07
    cies
    -0.07
    hind
    -0.06
    ibraltar
    -0.06
    vier
    -0.06
    Ùħت
    -0.06
    ecies
    -0.06
    ysz
    -0.06
    bie
    -0.06
    çݲ
    -0.06
    POSITIVE LOGITS
    ún
    0.06
    UNS
    0.06
    isson
    0.06
    IRA
    0.06
    TAG
    0.06
    chn
    0.06
    ä¸ĺ
    0.06
     dog
    0.06
    бÑĥ
    0.06
    (strtolower
    0.06
    Activations Density 0.003%

    No Known Activations