© 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. 6-LLAMASCOPE-RES-32K
    6. 5971
    Prev
    Next
    INDEX
    Explanations

    references to legal actions or terms related to arrest warrants

    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
    asar
    -0.17
     Pom
    -0.15
     pres
    -0.14
     Nest
    -0.14
    èĨľ
    -0.14
    IndexOf
    -0.14
     Reg
    -0.13
     Camp
    -0.13
    nest
    -0.13
     Plot
    -0.13
    POSITIVE LOGITS
    AGMA
    0.15
    ashboard
    0.15
    735
    0.14
    qus
    0.14
     Sexo
    0.14
    å¾³
    0.14
    resses
    0.14
    äng
    0.13
    .Annotations
    0.13
    itches
    0.13
    Activations Density 0.013%

    No Known Activations