© 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. 22-LLAMASCOPE-RES-131K
    11. 4188
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values

    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
    onda
    -0.07
    andan
    -0.07
    elmet
    -0.07
    InvalidOperationException
    -0.07
    olume
    -0.06
    esch
    -0.06
    rikes
    -0.06
    lete
    -0.06
    ekil
    -0.06
    },{"
    -0.06
    POSITIVE LOGITS
    heim
    0.07
     importance
    0.07
    972
    0.06
     important
    0.06
    important
    0.06
    FFE
    0.06
    .AttributeSet
    0.06
    顾
    0.05
    ONO
    0.05
     NOP
    0.05
    Activations Density 0.001%

    No Known Activations