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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5758
    Prev
    Next
    INDEX
    Explanations

    typographic or font-related terms

    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
    ihn
    -0.08
    bsite
    -0.07
    gn
    -0.06
    ldre
    -0.06
    oque
    -0.06
    rok
    -0.06
    prot
    -0.06
    acct
    -0.06
    gran
    -0.06
    edes
    -0.06
    POSITIVE LOGITS
    -Bold
    0.08
    -Regular
    0.08
    itals
    0.08
    .ttf
    0.07
     Cond
    0.07
     Bold
    0.07
     Expert
    0.07
     Regular
    0.07
    -normal
    0.07
     Experts
    0.07
    Activations Density 0.002%

    No Known Activations