© 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. 20-LLAMASCOPE-RES-32K
    11. 11185
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate attempts or actions being completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attempt
    -0.19
     attempting
    -0.19
     necessarily
    -0.16
    èĥ½å¤Ł
    -0.16
     Attempt
    -0.16
     trying
    -0.15
    .try
    -0.15
     attempts
    -0.15
     attempted
    -0.15
     try
    -0.15
    POSITIVE LOGITS
    -ÑĤаки
    0.20
    LATED
    0.16
     convince
    0.15
    \common
    0.15
    eselect
    0.14
    lexer
    0.14
     quite
    0.14
    addtogroup
    0.14
    rought
    0.14
     dual
    0.14
    Activations Density 0.056%

    No Known Activations