© 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. 27-LLAMASCOPE-RES-32K
    11. 19056
    Prev
    Next
    INDEX
    Explanations

    the word "little" 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 @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uality
    -0.17
    landa
    -0.17
    oe
    -0.17
    /doc
    -0.15
    i
    -0.15
    ron
    -0.14
    ing
    -0.14
    eded
    -0.14
    apesh
    -0.14
    ÙĪÙ¾
    -0.14
    POSITIVE LOGITS
     bit
    0.38
    -known
    0.34
    -bit
    0.31
    bit
    0.29
    Bits
    0.26
    .bit
    0.25
    /big
    0.24
    _bit
    0.23
    /tiny
    0.22
     Bit
    0.22
    Activations Density 0.050%

    No Known Activations