© 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. 61144
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" within the text

    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
    idl
    -0.07
    ory
    -0.06
    768
    -0.06
    IDL
    -0.06
    .measure
    -0.06
     Cust
    -0.06
    anno
    -0.05
     eiusmod
    -0.05
    541
    -0.05
     .
    -0.05
    POSITIVE LOGITS
     size
    0.13
    size
    0.09
     scope
    0.09
     magnitude
    0.09
     stature
    0.09
     length
    0.09
     amount
    0.08
    è§Ħ模
    0.08
     intensity
    0.08
     duration
    0.08
    Activations Density 0.097%

    No Known Activations