© 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. 75160
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance metrics and optimization tasks

    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
    dsl
    -0.07
     «
    -0.06
    .;
    -0.06
    JNI
    -0.06
    );\↵
    -0.06
     #-
    -0.06
    ')↵
    -0.06
    ÂŃ
    -0.06
     _
    -0.06
    /Dk
    -0.06
    POSITIVE LOGITS
    ](
    0.11
    }
    0.10
    ãĢĭ
    0.08
    #else
    0.08
    âĢ¬
    0.07
     ]
    0.07
     ></
    0.07
    ...]
    0.07
    <\/
    0.07
    ]
    0.07
    Activations Density 0.090%

    No Known Activations