© 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. 28-LLAMASCOPE-RES-32K
    6. 30087
    Prev
    Next
    INDEX
    Explanations

    elements pertaining to local government and community activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agra
    -0.15
    itrust
    -0.15
     antig
    -0.14
    _checkout
    -0.14
    mix
    -0.14
     tém
    -0.14
     Ear
    -0.14
    .snp
    -0.13
    .gc
    -0.13
     ÑĤÑĢÑĥ
    -0.13
    POSITIVE LOGITS
     Somerset
    0.32
     Ta
    0.29
    Ta
    0.26
    Som
    0.24
    -Ta
    0.24
     som
    0.23
     Mend
    0.23
     Mine
    0.22
    Mine
    0.21
     TA
    0.20
    Activations Density 0.012%

    No Known Activations