© 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. 78291
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate location or context in relation to actions

    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
    á»įc
    -0.08
    readcr
    -0.08
    AndPassword
    -0.08
    .scalablytyped
    -0.08
    ạnh
    -0.07
    isiyle
    -0.07
     somewhat
    -0.07
    .notNull
    -0.07
     нада
    -0.07
    UNUSED
    -0.07
    POSITIVE LOGITS
     nor
    0.25
     anymore
    0.20
     either
    0.20
    nor
    0.16
     anywhere
    0.16
     except
    0.15
     or
    0.15
    either
    0.15
     neither
    0.14
     Nor
    0.14
    Activations Density 0.085%

    No Known Activations