© 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. 15-LLAMASCOPE-RES-131K
    11. 103832
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting symbols

    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
    arch
    -0.06
    .cn
    -0.06
    pherical
    -0.06
    x
    -0.06
    pulse
    -0.06
    pg
    -0.06
     limits
    -0.06
     pulse
    -0.06
    elines
    -0.05
     Arm
    -0.05
    POSITIVE LOGITS
    STANCE
    0.09
    isay
    0.08
    ưỡng
    0.07
    acente
    0.07
    ogle
    0.07
    ITH
    0.07
    ģm
    0.07
    inizi
    0.07
    alink
    0.07
     Uns
    0.07
    Activations Density 0.028%

    No Known Activations