© 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. 87242
    Prev
    Next
    INDEX
    Explanations

    information related to contact details and affiliations

    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
    å¾
    -0.07
    ieren
    -0.06
    ritt
    -0.06
    quet
    -0.06
    åIJį稱
    -0.06
    ubat
    -0.06
    ingu
    -0.06
     Names
    -0.06
    çĽĬ
    -0.06
    idon
    -0.06
    POSITIVE LOGITS
    email
    0.07
     bio
    0.07
    infeld
    0.07
    mailto
    0.07
     Vive
    0.07
    'email
    0.07
     email
    0.07
    Bio
    0.06
    _bio
    0.06
    .email
    0.06
    Activations Density 0.008%

    No Known Activations