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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-LLAMASCOPE-RES-32K
    6. 7763
    Prev
    Next
    INDEX
    Explanations

    names of prominent individuals and their relationships in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endor
    -0.16
    Č
    -0.15
    ocab
    -0.15
    cia
    -0.15
    avor
    -0.14
    otas
    -0.14
    å»·
    -0.14
    fos
    -0.14
    -val
    -0.14
    gis
    -0.13
    POSITIVE LOGITS
    ÑģÑĤи
    0.15
    rites
    0.14
    μÎŃνα
    0.14
    éĢĨ
    0.14
    »
    0.14
    .NULL
    0.14
    izr
    0.13
    idence
    0.13
    #$
    0.13
    ayed
    0.13
    Activations Density 0.005%

    No Known Activations