© 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. 126458
    Prev
    Next
    INDEX
    Explanations

    various elements and attributes of software package documentation

    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
    ,
    -0.07
    1
    -0.06
    .
    -0.06
    ↵
    -0.06
    6
    -0.06
    255
    -0.05
     Bi
    -0.05
    5
    -0.05
    -0.05
     bi
    -0.05
    POSITIVE LOGITS
    å±ĭ
    0.10
    ENCH
    0.09
    .fil
    0.09
    ÅĻes
    0.09
    سÙĦ
    0.09
    .gf
    0.09
    argout
    0.08
    ï¼
    0.08
    ÎĪ
    0.08
    ÎĨ
    0.08
    Activations Density 0.005%

    No Known Activations