© 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. 10899
    Prev
    Next
    INDEX
    Explanations

    phrases indicating record achievements or milestones

    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
    isan
    -0.16
    ardin
    -0.16
    inch
    -0.14
    Unexpected
    -0.14
     ust
    -0.14
    plied
    -0.13
    yc
    -0.13
    aves
    -0.13
    stants
    -0.13
    /internal
    -0.13
    POSITIVE LOGITS
    -breaking
    0.47
    breaking
    0.44
     breaking
    0.40
    -setting
    0.40
     Breaking
    0.35
    Breaking
    0.34
    setting
    0.31
     breaker
    0.30
    -break
    0.29
     setting
    0.29
    Activations Density 0.017%

    No Known Activations