© 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. 2-LLAMASCOPE-RES-32K
    11. 422
    Prev
    Next
    INDEX
    Explanations

    specific programming or technical terms associated with development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Convention
    -0.16
    [sub
    -0.16
    .ma
    -0.16
     stripped
    -0.15
    _lite
    -0.15
    lobal
    -0.15
    oleans
    -0.14
    ockey
    -0.14
    æľ«
    -0.14
    ãĥ¼ãĥ«ãĥī
    -0.14
    POSITIVE LOGITS
    aled
    0.18
    871
    0.16
    ars
    0.15
     incur
    0.15
    vel
    0.14
    ledged
    0.14
    linger
    0.14
    noon
    0.14
     rep
    0.14
    sted
    0.14
    Activations Density 0.367%

    No Known Activations