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. 14-LLAMASCOPE-RES-32K
    6. 32049
    Prev
    Next
    INDEX
    Explanations

    terms related to user account management and password reset processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /stdc
    -0.19
     licence
    -0.15
     Licence
    -0.15
    cue
    -0.14
    hook
    -0.14
     lic
    -0.14
     Werk
    -0.14
     licences
    -0.14
    _checks
    -0.14
     commission
    -0.14
    POSITIVE LOGITS
    磨
    0.15
    ulumi
    0.15
    assed
    0.14
     ATK
    0.14
    voke
    0.14
     å¼
    0.14
    _attempts
    0.14
    温
    0.13
     haz
    0.13
     assistance
    0.13
    Activations Density 0.017%

    No Known Activations