© 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. 30-LLAMASCOPE-RES-32K
    11. 11458
    Prev
    Next
    INDEX
    Explanations

    the word "won" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tures
    -0.18
    yar
    -0.16
    주ëĬĶ
    -0.16
    /Delete
    -0.15
    inem
    -0.15
    egin
    -0.14
    tin
    -0.14
    ials
    -0.14
    datable
    -0.14
     useForm
    -0.13
    POSITIVE LOGITS
    't
    0.41
    ’t
    0.35
    'T
    0.23
    ;t
    0.23
    ´t
    0.22
    def
    0.18
    `t
    0.18
    ked
    0.17
    DER
    0.17
    k
    0.17
    Activations Density 0.037%

    No Known Activations