Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 87452
    Prev
    Next
    INDEX
    Explanations

    terms relating to the consequences and effects of actions or events

    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
    ynet
    -0.07
    AREST
    -0.07
    ông
    -0.06
    dge
    -0.06
    imar
    -0.06
    ordinator
    -0.06
    AXB
    -0.06
    uchar
    -0.06
    inki
    -0.06
    Clr
    -0.06
    POSITIVE LOGITS
     upon
    0.09
     on
    0.08
    igue
    0.07
    SI
    0.07
     Upon
    0.06
    583
    0.06
     عÙĦÙī
    0.06
    ãĤ§
    0.06
    STALL
    0.06
     عÙĦÙĬÙĩ
    0.06
    Activations Density 0.014%

    No Known Activations