Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 7-LLAMASCOPE-RES-32K
    6. 17518
    Prev
    Next
    INDEX
    Explanations

    structured data types, variables, and their relationships in programming contexts

    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
    tera
    -0.18
    лÑıд
    -0.16
     Pierce
    -0.15
    edException
    -0.15
    à¸Ħว
    -0.15
    elt
    -0.15
    atas
    -0.15
    ATUS
    -0.14
    CP
    -0.14
    ter
    -0.14
    POSITIVE LOGITS
    -to
    0.18
    reas
    0.17
     <->
    0.16
     <=>
    0.16
     strengths
    0.15
    atre
    0.15
    -and
    0.14
    resher
    0.14
    SCALL
    0.14
    &o
    0.14
    Activations Density 0.339%

    No Known Activations