© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 16-LLAMASCOPE-RES-32K
    11. 22274
    Prev
    Next
    INDEX
    Explanations

    components and features related to assessment and evaluation systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alis
    -0.15
    -0.15
    ija
    -0.14
    eltas
    -0.13
     Shorts
    -0.13
    atan
    -0.13
    999
    -0.13
    ental
    -0.13
     Huss
    -0.13
     fitness
    -0.13
    POSITIVE LOGITS
    abase
    0.23
     výbÄĽ
    0.16
    ETO
    0.15
    ÑĨвеÑĤ
    0.15
    _FA
    0.15
    craper
    0.15
    Ñģов
    0.15
     Auswahl
    0.15
    _choose
    0.14
     initially
    0.14
    Activations Density 0.320%

    No Known Activations