© 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. 22-LLAMASCOPE-RES-32K
    11. 11579
    Prev
    Next
    INDEX
    Explanations

    negative traits or behaviors in characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACHI
    -0.15
    овиÑĩ
    -0.15
    owi
    -0.15
    ixin
    -0.14
    agus
    -0.13
    ablo
    -0.13
    alted
    -0.13
    abajo
    -0.13
    vida
    -0.13
    anio
    -0.13
    POSITIVE LOGITS
     writers
    0.17
     week
    0.15
     tv
    0.15
     Writers
    0.15
     episode
    0.15
    äºĮ人
    0.15
    alth
    0.15
     season
    0.15
    vier
    0.15
     scenes
    0.15
    Activations Density 0.096%

    No Known Activations