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. 31-LLAMASCOPE-RES-32K
    6. 6457
    Prev
    Next
    INDEX
    Explanations

    phrases or words that emphasize a singular or unique quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whichever
    -0.14
     whatever
    -0.14
    ended
    -0.14
    好ãģį
    -0.14
     Äįin
    -0.13
    cken
    -0.13
     respectively
    -0.13
     overposting
    -0.13
    lessly
    -0.13
    oogle
    -0.13
    POSITIVE LOGITS
     thing
    0.41
     way
    0.31
     remaining
    0.29
     place
    0.28
     exception
    0.28
     reason
    0.27
     real
    0.26
     conceivable
    0.26
     ones
    0.26
     difference
    0.25
    Activations Density 0.067%

    No Known Activations