Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44225
    Prev
    Next
    INDEX
    Explanations

    references to exceptions and errors in code

    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
     
    -0.14
     and
    -0.12
     the
    -0.10
     to
    -0.10
     a
    -0.10
     as
    -0.09
    .
    -0.09
     })
    -0.09
    ,
    -0.09
     with
    -0.09
    POSITIVE LOGITS
    }↵↵
    0.15
    }↵
    0.15
    ]↵
    0.11
    »↵↵
    0.11
    »↵
    0.11
    ]↵↵
    0.11
    )↵↵
    0.10
    ’↵↵
    0.10
    )↵
    0.10
    }↵↵↵
    0.10
    Activations Density 0.019%

    No Known Activations