© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60847
    Prev
    Next
    INDEX
    Explanations

    phrases indicating locations and settings

    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
    ubb
    -0.07
    hower
    -0.07
    cir
    -0.06
     rigor
    -0.06
     concept
    -0.06
    Introduced
    -0.06
    ãĥ¼ãĥĸ
    -0.06
    ngth
    -0.06
    ediator
    -0.06
    ubs
    -0.06
    POSITIVE LOGITS
    orz
    0.07
     Ward
    0.06
    788
    0.06
     JpaRepository
    0.06
    Ñĩен
    0.06
    iktig
    0.06
     GlobalKey
    0.06
    egov
    0.06
    PT
    0.06
     Accepted
    0.06
    Activations Density 0.013%

    No Known Activations