© 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. 31-LLAMASCOPE-RES-32K
    11. 9772
    Prev
    Next
    INDEX
    Explanations

    words associated with legal or regulatory actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anness
    -0.18
    yses
    -0.17
    alysis
    -0.17
    eners
    -0.16
    usterity
    -0.15
    ysis
    -0.15
    atcher
    -0.15
    izing
    -0.15
    verity
    -0.15
    ization
    -0.14
    POSITIVE LOGITS
    ado
    0.44
    ada
    0.36
    ados
    0.35
    izado
    0.33
    adas
    0.31
    ADO
    0.31
    cido
    0.30
    rado
    0.30
    iado
    0.29
    ificado
    0.29
    Activations Density 0.031%

    No Known Activations