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. 11-LLAMASCOPE-RES-32K
    6. 845
    Prev
    Next
    INDEX
    Explanations

    technical specifications or components in machinery and coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ABCDEFG
    -0.15
    .mods
    -0.15
     spectator
    -0.14
    ARED
    -0.14
    IALOG
    -0.13
    illos
    -0.13
    aze
    -0.13
    ahren
    -0.13
    _Ptr
    -0.13
    icine
    -0.13
    POSITIVE LOGITS
    obb
    0.16
    lever
    0.15
    eed
    0.14
    graf
    0.14
    hait
    0.14
    perf
    0.14
     Lastly
    0.14
     خاÙħ
    0.14
    zen
    0.13
    rella
    0.13
    Activations Density 0.150%

    No Known Activations