© 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. 30-LLAMASCOPE-RES-32K
    6. 22943
    Prev
    Next
    INDEX
    Explanations

    references to sports terminology and related concepts

    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
    rade
    -0.15
    áÅĻ
    -0.15
    atra
    -0.14
    .WriteByte
    -0.13
    erez
    -0.13
    Reusable
    -0.13
     Reco
    -0.13
    RectTransform
    -0.13
    анÑĤаж
    -0.13
    ERSION
    -0.13
    POSITIVE LOGITS
     run
    1.32
     runs
    1.16
     Run
    1.14
    run
    1.11
     ran
    1.09
    Run
    1.08
    -run
    1.07
     running
    1.06
    .run
    1.05
     RUN
    1.05
    Activations Density 0.504%

    No Known Activations