© 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. 25-LLAMASCOPE-RES-32K
    11. 22928
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to knowledge and awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OLLOW
    -0.16
    chyb
    -0.16
    .scalablytyped
    -0.15
    umi
    -0.15
    gnu
    -0.15
    _UNUSED
    -0.15
    regon
    -0.14
    jure
    -0.14
    ungen
    -0.14
    ä¸įè¦ģ
    -0.14
    POSITIVE LOGITS
     zero
    0.48
     absolutely
    0.42
     little
    0.42
     ZERO
    0.39
    zero
    0.39
     Zero
    0.39
    little
    0.37
    -zero
    0.37
    Zero
    0.36
    _zero
    0.34
    Activations Density 0.198%

    No Known Activations