© 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. 6-LLAMASCOPE-RES-32K
    11. 10189
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to various types of direction or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardy
    -0.18
    çŃĭ
    -0.15
    iquer
    -0.15
    InitialState
    -0.15
    евиÑĩ
    -0.15
     Äijoán
    -0.14
    itung
    -0.14
    elpers
    -0.14
    .constants
    -0.14
    ä¼´
    -0.14
    POSITIVE LOGITS
    ally
    0.20
     directions
    0.18
     direction
    0.17
     Directions
    0.15
    weis
    0.15
    397
    0.15
    sha
    0.15
    ality
    0.15
    direction
    0.15
    ales
    0.14
    Activations Density 0.046%

    No Known Activations