© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 10989
    Prev
    Next
    INDEX
    Explanations

    terms related to analysis and assessments involved in various scientific or evaluative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avn
    -0.16
    å¦
    -0.15
    hle
    -0.13
    ckill
    -0.13
    ụ
    -0.12
    oenix
    -0.12
    otron
    -0.12
    oref
    -0.12
    )(((
    -0.12
    upakan
    -0.12
    POSITIVE LOGITS
     at
    0.94
     tại
    0.54
    _at
    0.51
    èĩ³å°ij
    0.47
    	at
    0.47
    .at
    0.41
    at
    0.41
    At
    0.40
     ợ
    0.40
     atIndex
    0.40
    Activations Density 0.165%

    No Known Activations