© 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. 56252
    Prev
    Next
    INDEX
    Explanations

    phrases related to extracting or removing something

    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
    á»ĩ
    -0.07
     Balls
    -0.07
    vore
    -0.07
    íĻĺ
    -0.07
     balls
    -0.07
     ball
    -0.07
    íĮĮ
    -0.07
     bounced
    -0.07
    etch
    -0.07
    çIJĥ
    -0.07
    POSITIVE LOGITS
    pull
    0.13
    Pull
    0.12
     pulling
    0.12
     pull
    0.12
     Pull
    0.12
     pulls
    0.11
     pulled
    0.10
    .Pull
    0.10
     plug
    0.09
    _pull
    0.09
    Activations Density 0.026%

    No Known Activations