© 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. 29-LLAMASCOPE-RES-32K
    11. 4681
    Prev
    Next
    INDEX
    Explanations

    citations from academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ildo
    -0.15
    UILTIN
    -0.15
    ihad
    -0.15
     Shane
    -0.14
    strup
    -0.14
    seau
    -0.14
    -heading
    -0.14
    istor
    -0.14
    edral
    -0.14
     ZIP
    -0.14
    POSITIVE LOGITS
     Mitar
    0.18
     Burada
    0.15
    _PHYS
    0.15
    flen
    0.15
     Perth
    0.15
    HEMA
    0.15
    èķī
    0.15
    pcb
    0.14
     Padding
    0.14
     Lakes
    0.14
    Activations Density 0.025%

    No Known Activations