© 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. 23-LLAMASCOPE-RES-32K
    11. 27931
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS structure within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ought
    -0.17
    iele
    -0.16
     foot
    -0.16
    fak
    -0.15
    pk
    -0.15
    ofilm
    -0.15
    /apt
    -0.15
    iral
    -0.15
    adows
    -0.15
    ">//
    -0.15
    POSITIVE LOGITS
    /logo
    0.26
     logo
    0.25
    logo
    0.25
    -logo
    0.23
     Logo
    0.23
    .logo
    0.22
    Logo
    0.22
     brand
    0.21
    _logo
    0.20
    ħ§
    0.20
    Activations Density 0.024%

    No Known Activations