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. 18219
    Prev
    Next
    INDEX
    Explanations

    the presence of special characters or symbols within the text

    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
    owie
    -0.17
    adera
    -0.15
     addCriterion
    -0.15
    ziel
    -0.15
    testdata
    -0.14
    SetBranch
    -0.14
     setC
    -0.14
    -tested
    -0.14
    tram
    -0.14
    azu
    -0.14
    POSITIVE LOGITS
    aff
    0.19
     aff
    0.18
     hand
    0.18
    Aff
    0.18
     hands
    0.18
     neck
    0.17
     Aff
    0.17
    _aff
    0.17
     affinity
    0.17
     shoulder
    0.17
    Activations Density 0.017%

    No Known Activations