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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5016
    Prev
    Next
    INDEX
    Explanations

    words related to scoring or numerical values

    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
     Petit
    -0.06
    495
    -0.06
    abus
    -0.06
    optera
    -0.06
    Specifier
    -0.05
    iam
    -0.05
    ¶ļ
    -0.05
    haf
    -0.05
    urette
    -0.05
    bourne
    -0.05
    POSITIVE LOGITS
    .Experimental
    0.07
    aintenance
    0.07
    ίÏĥ
    0.07
    ä»¶
    0.07
    onta
    0.06
    STRU
    0.06
    åĭ¢
    0.06
    otime
    0.06
    oro
    0.06
     canActivate
    0.06
    Activations Density 0.000%

    No Known Activations