© 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. 7-LLAMASCOPE-RES-32K
    11. 12059
    Prev
    Next
    INDEX
    Explanations

    CSS positioning properties and their related values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rape
    -0.15
    ittel
    -0.15
    aurus
    -0.15
    oby
    -0.15
    .mi
    -0.15
     Gem
    -0.14
    bler
    -0.14
    mant
    -0.14
    nicos
    -0.14
    STATIC
    -0.14
    POSITIVE LOGITS
    anz
    0.19
    ardu
    0.19
    ÐĤ
    0.17
    ony
    0.15
    antu
    0.15
    arding
    0.15
    colm
    0.15
    ards
    0.15
    istrovstvÃŃ
    0.14
    ARD
    0.14
    Activations Density 0.004%

    No Known Activations