INDEX

Explanations

terms related to legal classifications and categorizations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ond

-0.17

steen

-0.16

esktop

-0.16

Ð¾Ð½Ð´

-0.15

otide

-0.15

ibus

-0.15

ãĥ¼ãĤ

-0.15

Ð¾ÑĢÐ¼

-0.14

itorio

-0.14

fusion

-0.14

POSITIVE LOGITS

_DECLARE

0.15

ATER

0.15

0.14

ForMember

0.14

ray

0.14

ippo

0.14

 Continuous

0.14

 meets

0.13

 meet

0.13

Activations Density 0.148%

terms related to legal classifications and categorizations

No Comments

No Known Activations