© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 7-LLAMASCOPE-RES-32K
    6. 13936
    Prev
    Next
    INDEX
    Explanations

    instances of conflict or controversy related to community and individual interests

    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
    458
    -0.17
    aver
    -0.15
    neider
    -0.14
    #:
    -0.14
    ?=.*
    -0.14
    ši
    -0.13
    preset
    -0.13
    otes
    -0.13
    inker
    -0.13
    λαν
    -0.13
    POSITIVE LOGITS
    à¹Ħว
    0.16
     into
    0.16
     onto
    0.15
    Ñĥда
    0.14
    SHIP
    0.13
    egas
    0.13
    onto
    0.13
    onec
    0.13
    ijkstra
    0.13
    _draft
    0.13
    Activations Density 0.627%

    No Known Activations