© 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. 24-LLAMASCOPE-RES-32K
    11. 6249
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate a connection or continuation between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ses
    -0.28
    ↵
    -0.21
    nt
    -0.20
    /her
    -0.18
    ?s
    -0.17
    ÂŃs
    -0.17
    %s
    -0.17
    ’t
    -0.16
    -t
    -0.16
    \s
    -0.15
    POSITIVE LOGITS
    amp
    0.76
    nbsp
    0.48
    AMP
    0.45
    quot
    0.42
    raquo
    0.42
    ÑĶм
    0.38
    apos
    0.38
    ï¸ı
    0.30
     amp
    0.30
    emsp
    0.29
    Activations Density 0.064%

    No Known Activations