© 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. 9-LLAMASCOPE-RES-131K
    11. 95709
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    241
    -0.06
    atus
    -0.06
     dod
    -0.05
    127
    -0.05
    hz
    -0.05
    242
    -0.05
    ropic
    -0.05
    10
    -0.05
    udo
    -0.05
     sector
    -0.05
    POSITIVE LOGITS
    podob
    0.08
    avra
    0.08
    raÄį
    0.08
    istrov
    0.08
    .radioButton
    0.08
     Erotik
    0.08
     BÃŃ
    0.08
    ROUP
    0.08
    UILTIN
    0.07
    edback
    0.07
    Activations Density 0.015%

    No Known Activations