© 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. 25-LLAMASCOPE-RES-32K
    6. 16275
    Prev
    Next
    INDEX
    Explanations

    different forms of the verb "do"

    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
    umar
    -0.19
    538
    -0.16
    kar
    -0.15
    wy
    -0.15
    melon
    -0.15
    )((((
    -0.15
    ks
    -0.14
    ÄĻ
    -0.14
    mania
    -0.14
    w
    -0.14
    POSITIVE LOGITS
     precisely
    0.21
     just
    0.21
     otherwise
    0.20
     Ñģаме
    0.18
     exactly
    0.18
     wÅĤa
    0.17
     právÄĽ
    0.16
    uste
    0.16
    just
    0.16
     so
    0.16
    Activations Density 0.035%

    No Known Activations