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. 31-LLAMASCOPE-RES-32K
    6. 2242
    Prev
    Next
    INDEX
    Explanations

    quoted phrases and specific conditions related to reporting and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MX
    -0.24
    MF
    -0.23
    MM
    -0.22
    MZ
    -0.21
    /M
    -0.21
    MG
    -0.21
    MV
    -0.21
    MH
    -0.21
    MU
    -0.21
    MK
    -0.20
    POSITIVE LOGITS
     mother
    0.35
     menu
    0.33
     mission
    0.33
     menace
    0.33
     month
    0.33
     monthly
    0.32
     mothers
    0.32
     months
    0.32
     mouth
    0.32
     mention
    0.31
    Activations Density 0.398%

    No Known Activations