© 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. 78092
    Prev
    Next
    INDEX
    Explanations

    references to the word "Herz" and related terms, suggesting a focus on heart or related themes

    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
    gere
    -0.07
    resse
    -0.07
    ledge
    -0.07
    ra
    -0.06
    obi
    -0.06
    REFIX
    -0.06
    elic
    -0.06
    gether
    -0.06
    ertiary
    -0.06
    ASIC
    -0.06
    POSITIVE LOGITS
    encia
    0.08
    igon
    0.08
    aceous
    0.08
    amient
    0.07
    egov
    0.07
    aint
    0.07
    ERSHEY
    0.07
    uida
    0.07
    oving
    0.07
    ect
    0.07
    Activations Density 0.028%

    No Known Activations