Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 11734
    Prev
    Next
    INDEX
    Explanations

    references to various animals, particularly birds and reptiles

    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
    orative
    -0.16
    edImage
    -0.16
    uries
    -0.15
    ?action
    -0.15
     horses
    -0.15
    omo
    -0.14
    quares
    -0.14
     tiger
    -0.14
     iy
    -0.14
    imes
    -0.14
    POSITIVE LOGITS
    skin
    0.24
    tail
    0.21
    -shaped
    0.21
    foot
    0.21
    kin
    0.20
     tail
    0.20
    ishly
    0.19
    /go
    0.19
    -headed
    0.19
    bane
    0.18
    Activations Density 0.138%

    No Known Activations