© 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. 1444
    Prev
    Next
    INDEX
    Explanations

    references to signing or endorsing documents

    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
    áo
    -0.16
    enses
    -0.14
    ograd
    -0.14
    ษ
    -0.13
    _charset
    -0.13
    ynchronized
    -0.13
    enschaft
    -0.13
     Ø´Ùģ
    -0.13
    ÑĢоиз
    -0.13
    íĨ¡
    -0.12
    POSITIVE LOGITS
     signing
    1.19
     signed
    1.13
     signature
    1.08
     signatures
    1.06
     Signing
    1.04
     Signed
    0.99
     signer
    0.98
    çŃ¾
    0.97
    signed
    0.97
     Signature
    0.96
    Activations Density 0.371%

    No Known Activations