© 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. 105910
    Prev
    Next
    INDEX
    Explanations

    instructions related to filling out forms or completing applications

    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
     itself
    -0.08
     gens
    -0.07
    uje
    -0.07
    325
    -0.06
    327
    -0.06
     hers
    -0.06
    osti
    -0.06
    txn
    -0.06
    ep
    -0.06
    igg
    -0.06
    POSITIVE LOGITS
     following
    0.07
    以ä¸ĭ
    0.07
    ekli
    0.07
     ÑģледÑĥÑİÑī
    0.07
     aÅŁaģıdaki
    0.07
    ctors
    0.07
     our
    0.07
     Fahr
    0.06
     vår
    0.06
    ä¸Ģä¸ĭ
    0.06
    Activations Density 0.025%

    No Known Activations