© 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. 118863
    Prev
    Next
    INDEX
    Explanations

    words indicating sections of a timeline or events around governmental changes

    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
    изнеÑģ
    -0.07
    _MALLOC
    -0.06
    eturn
    -0.06
     *(*
    -0.06
     комÑĥ
    -0.06
    edList
    -0.06
    theid
    -0.06
    ONS
    -0.06
    utm
    -0.06
    ime
    -0.06
    POSITIVE LOGITS
    ologically
    0.09
    enk
    0.08
     same
    0.07
    urally
    0.07
    tern
    0.07
    oret
    0.07
    ough
    0.07
    isel
    0.07
    tas
    0.07
    omorphic
    0.07
    Activations Density 0.011%

    No Known Activations