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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40572
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a group context or collective membership

    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
    orent
    -0.07
     PMID
    -0.06
    iti
    -0.06
    zac
    -0.06
    yards
    -0.06
    .Aggressive
    -0.06
    pedia
    -0.05
    @brief
    -0.05
    ider
    -0.05
    overs
    -0.05
    POSITIVE LOGITS
    erset
    0.07
    aucoup
    0.07
    edly
    0.07
    bk
    0.07
    ffset
    0.07
    ledon
    0.07
    ains
    0.07
    ezi
    0.07
     astore
    0.07
    ADOR
    0.07
    Activations Density 0.008%

    No Known Activations