INDEX

Explanations

references to law enforcement and investigative actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

rella

-0.15

gue

-0.15

 writ

-0.15

steen

-0.14

Î³Î·

-0.14

_province

-0.14

Î¬Ïĥ

-0.14

ãĥ«ãĤ¯

-0.14

aight

-0.14

cych

-0.13

POSITIVE LOGITS

 cord

0.19

say

0.19

 confisc

0.18

 arrest

0.17

 searching

0.17

iez

0.16

 said

0.16

egin

0.15

 Searching

0.15

say

0.15

Activations Density 0.048%

references to law enforcement and investigative actions

No Comments

No Known Activations