© 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. 56323
    Prev
    Next
    INDEX
    Explanations

    dates and references to months within a historical context

    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
    ieber
    -0.07
    oir
    -0.07
    alic
    -0.07
    iza
    -0.07
    enga
    -0.07
    RESH
    -0.06
     infix
    -0.06
    Reader
    -0.06
    Ä±ÅŁÄ±k
    -0.06
    ensa
    -0.06
    POSITIVE LOGITS
    ham
    0.07
    embro
    0.07
    ombat
    0.06
    imesteps
    0.06
    NavController
    0.06
    orch
    0.06
    :uint
    0.06
    arten
    0.06
    iciary
    0.06
    _kses
    0.06
    Activations Density 0.005%

    No Known Activations