© 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. 28-LLAMASCOPE-RES-32K
    6. 23017
    Prev
    Next
    INDEX
    Explanations

    contrasting descriptions of people or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸
    -0.15
    able
    -0.14
    kinson
    -0.14
    ible
    -0.14
    versible
    -0.14
    elah
    -0.14
    oken
    -0.14
    _FIXED
    -0.14
    ville
    -0.13
     Harm
    -0.13
    POSITIVE LOGITS
     yet
    0.21
     occasionally
    0.21
    yet
    0.17
    .ActionListener
    0.17
     sometimes
    0.17
     ÑĩаÑģом
    0.15
     prof
    0.15
    ometimes
    0.15
     moving
    0.15
    beautiful
    0.15
    Activations Density 0.114%

    No Known Activations