© 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. 27-LLAMASCOPE-RES-32K
    11. 12512
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was" and other related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erotico
    -0.16
    izoph
    -0.15
    aft
    -0.15
    ekk
    -0.14
    @qq
    -0.14
    ileged
    -0.14
    obsolete
    -0.14
    ÙĦÙĩ
    -0.14
    venir
    -0.14
    ncy
    -0.14
    POSITIVE LOGITS
     seen
    0.24
     spotted
    0.23
     mob
    0.22
     candid
    0.22
    Seen
    0.20
    寿
    0.18
     photographed
    0.18
     coy
    0.18
     pictured
    0.18
     emotional
    0.18
    Activations Density 0.098%

    No Known Activations