© 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. 26-LLAMASCOPE-RES-32K
    11. 1276
    Prev
    Next
    INDEX
    Explanations

    phrases focused on responsibility and assurance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    must
    -0.19
     Must
    -0.19
    Must
    -0.18
    .must
    -0.18
     must
    -0.17
    isNaN
    -0.17
     trebuie
    -0.16
     seemed
    -0.16
    may
    -0.16
    é¡»
    -0.16
    POSITIVE LOGITS
     stays
    0.27
     stay
    0.25
     remains
    0.25
     remain
    0.24
    stay
    0.23
     properly
    0.22
     stayed
    0.22
     doesn
    0.22
     remained
    0.21
     Stay
    0.21
    Activations Density 0.249%

    No Known Activations