© 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. 7-LLAMASCOPE-RES-32K
    11. 20464
    Prev
    Next
    INDEX
    Explanations

    actions related to bending or leaning downward

    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
    eneg
    -0.18
    onas
    -0.17
    ugin
    -0.17
    iali
    -0.15
     pac
    -0.14
    utin
    -0.14
    onaut
    -0.14
    abeth
    -0.14
    icana
    -0.14
    ubat
    -0.14
    POSITIVE LOGITS
    erek
    0.16
     Adopt
    0.15
    AVIS
    0.15
    lv
    0.14
    otti
    0.14
    éĸĢ
    0.14
    essel
    0.13
    annon
    0.13
    igo
    0.13
    533
    0.13
    Activations Density 0.043%

    No Known Activations