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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 24403
    Prev
    Next
    INDEX
    Explanations

    references to legal penalties and reparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ViewState
    -0.15
    deaux
    -0.15
    otten
    -0.15
    atsby
    -0.15
     DISCLAIM
    -0.15
    ooter
    -0.14
     exit
    -0.14
    .cgi
    -0.14
    Margins
    -0.14
    _lex
    -0.14
    POSITIVE LOGITS
     mag
    0.23
     disqualified
    0.19
     Mag
    0.19
     Recorder
    0.19
     crown
    0.18
     Crown
    0.18
     recorder
    0.17
     adj
    0.17
    Recorder
    0.17
    Mag
    0.17
    Activations Density 0.011%

    No Known Activations