© 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. 10170
    Prev
    Next
    INDEX
    Explanations

    concepts related to accountability and consequences

    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
    kas
    -0.16
    olley
    -0.16
    oplast
    -0.15
    STANCE
    -0.15
    ube
    -0.15
    éĸĢ
    -0.14
    ɵ
    -0.14
    ouve
    -0.14
     بÙĦÙĨد
    -0.14
    éĢĶ
    -0.13
    POSITIVE LOGITS
     effort
    0.17
     Leer
    0.15
    oppins
    0.15
    _IRQ
    0.14
    arme
    0.14
     efforts
    0.14
    itsu
    0.14
    rello
    0.13
    phanumeric
    0.13
     Luck
    0.13
    Activations Density 0.114%

    No Known Activations