INDEX

Explanations

references to sexual orientation and gender identity issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

íĨµ

-0.17

rray

-0.17

mlink

-0.16

mpp

-0.16

ãĥ¼ãĥ©

-0.15

ranÃŃ

-0.15

ibre

-0.15

çĴ°

-0.15

ufen

-0.15

 trivia

-0.14

POSITIVE LOGITS

Ð¾Ð´Ð¾

0.18

bis

0.18

sod

0.17

bis

0.17

 trans

0.15

GL

0.15

Bis

0.15

dba

0.15

bash

0.15

ãĥ³ãĥĲ

0.14

Activations Density 0.122%

references to sexual orientation and gender identity issues

No Comments

No Known Activations