© 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. 9-LLAMASCOPE-RES-32K
    11. 3780
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to "pre" and its variations, often in a context that indicates prior conditions or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ser
    -0.16
    antan
    -0.16
    sh
    -0.16
    reas
    -0.16
    c
    -0.15
    v
    -0.15
    ref
    -0.15
    recht
    -0.15
    la
    -0.14
    sole
    -0.14
    POSITIVE LOGITS
    ursors
    0.19
    sed
    0.18
    ongyang
    0.17
    ÐĦ
    0.17
    yonel
    0.16
    /post
    0.16
    ted
    0.16
    PFN
    0.15
    AGMA
    0.15
    eor
    0.15
    Activations Density 0.068%

    No Known Activations