© 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. 27-LLAMASCOPE-RES-32K
    11. 10906
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or directives involving the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .MixedReality
    -0.16
    TouchUpInside
    -0.16
    cba
    -0.16
     DISCLAIM
    -0.15
    eras
    -0.14
    urer
    -0.14
    isbury
    -0.14
    createTime
    -0.14
    ÑģÑĤа
    -0.14
    azi
    -0.14
    POSITIVE LOGITS
     accompany
    0.25
     boot
    0.24
     tide
    0.24
     accompanies
    0.23
     Tide
    0.23
    -boot
    0.23
     suit
    0.20
     help
    0.19
    fits
    0.19
     behold
    0.19
    Activations Density 0.134%

    No Known Activations