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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-LLAMASCOPE-RES-32K
    6. 16561
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles within a specific context or story

    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
    dos
    -0.16
    ÃĹ↵↵
    -0.15
    ough
    -0.15
    )animated
    -0.15
    oba
    -0.15
    tright
    -0.15
    vů
    -0.14
    REEN
    -0.14
    apia
    -0.14
    angi
    -0.14
    POSITIVE LOGITS
    _D
    0.38
    -d
    0.36
     ãĥĩ
    0.35
    Âłd
    0.34
     ÐĶ
    0.34
     ड
    0.34
    _d
    0.33
    -D
    0.32
    'D
    0.31
     द
    0.31
    Activations Density 0.721%

    No Known Activations