© 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. 55899
    Prev
    Next
    INDEX
    Explanations

    references to groups, organizations, or affiliations

    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
    entiful
    -0.08
    assin
    -0.08
    .getSelection
    -0.08
    elyn
    -0.08
    iez
    -0.08
    ebek
    -0.07
    agedList
    -0.07
    lisi
    -0.07
    ierarchy
    -0.07
    amac
    -0.07
    POSITIVE LOGITS
    ims
    0.06
     CMP
    0.06
     several
    0.06
    766
    0.06
     about
    0.06
    ag
    0.06
    about
    0.06
     ash
    0.05
    &C
    0.05
    ash
    0.05
    Activations Density 0.020%

    No Known Activations