© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56460
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "left" in various contexts

    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
    MOTE
    -0.07
    ceptar
    -0.07
    edy
    -0.06
    yth
    -0.06
    dam
    -0.06
    iest
    -0.06
    .scalablytyped
    -0.06
    ãĤ
    -0.06
    olin
    -0.06
    parallel
    -0.06
    POSITIVE LOGITS
    uentes
    0.07
    ober
    0.07
    HeaderView
    0.06
    odore
    0.06
    361
    0.06
     JpaRepository
    0.06
    QueryParam
    0.06
    926
    0.06
    956
    0.06
    ExecutionContext
    0.06
    Activations Density 0.025%

    No Known Activations