© 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. 57226
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs indicating loops and conditionals

    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
    rien
    -0.08
    elle
    -0.07
    ellant
    -0.07
    ÏĦÏģο
    -0.06
    iazza
    -0.06
    _UNUSED
    -0.06
     Bilim
    -0.06
    wyn
    -0.06
    elm
    -0.06
    aviours
    -0.06
    POSITIVE LOGITS
    abis
    0.08
    uhe
    0.07
    vil
    0.07
    าะ
    0.07
    538
    0.06
    eless
    0.06
    plex
    0.06
    cljs
    0.06
    unfold
    0.06
    obil
    0.06
    Activations Density 0.001%

    No Known Activations