© 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. 27-LLAMASCOPE-RES-32K
    6. 19073
    Prev
    Next
    INDEX
    Explanations

    specific terms and concepts related to data organization and filtering in programming

    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
    ocache
    -0.14
    jvu
    -0.14
    idal
    -0.12
     سع
    -0.12
    Ïĥη
    -0.12
    _SEL
    -0.12
    sei
    -0.12
    aversable
    -0.12
    compileComponents
    -0.12
    VarChar
    -0.12
    POSITIVE LOGITS
     sub
    1.28
     Sub
    1.23
    sub
    1.18
    Sub
    1.12
    -sub
    1.07
    _sub
    1.03
    (sub
    0.98
     SUB
    0.98
    .sub
    0.96
    	sub
    0.92
    Activations Density 0.204%

    No Known Activations