© 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. 11481
    Prev
    Next
    INDEX
    Explanations

    questions being posed in the text

    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
    å®ĥ
    -0.21
    resident
    -0.17
    (it
    -0.16
    ï¼Įå®ĥ
    -0.15
    nelle
    -0.15
    It
    -0.15
    ,it
    -0.15
    aries
    -0.15
     nó
    -0.15
     Erot
    -0.15
    POSITIVE LOGITS
    /w
    0.27
     they
    0.26
    nt
    0.24
     we
    0.24
    ady
    0.23
    tha
    0.21
     these
    0.21
    /is
    0.21
     они
    0.20
     you
    0.20
    Activations Density 0.063%

    No Known Activations