© 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. 11-LLAMASCOPE-RES-32K
    6. 6978
    Prev
    Next
    INDEX
    Explanations

    CSS styles and their corresponding properties

    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
    annel
    -0.16
    IAS
    -0.16
    readcr
    -0.14
    eldorf
    -0.14
    okable
    -0.14
    omm
    -0.14
    onn
    -0.14
    odega
    -0.13
    rado
    -0.13
    .filtered
    -0.13
    POSITIVE LOGITS
    .gdx
    0.20
    nero
    0.14
    æŀĹ
    0.14
    éĬĢ
    0.14
    али
    0.14
    FindObject
    0.13
    eos
    0.13
     Hut
    0.13
    *)((
    0.13
    macı
    0.13
    Activations Density 0.007%

    No Known Activations