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. 44211
    Prev
    Next
    INDEX
    Explanations

    references to columns in a database or dataset

    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
    eden
    -0.08
    eve
    -0.07
    dna
    -0.07
    laden
    -0.07
    ees
    -0.07
    dal
    -0.07
    dq
    -0.07
    dol
    -0.07
    edImage
    -0.07
    eh
    -0.07
    POSITIVE LOGITS
    lected
    0.13
    ou
    0.12
    mn
    0.12
    ours
    0.12
    onne
    0.12
    ormap
    0.12
    una
    0.12
    unas
    0.12
    mun
    0.12
    apsed
    0.11
    Activations Density 0.011%

    No Known Activations