INDEX

Explanations

mentions or discussions of prejudice and discrimination

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

io

-0.16

anc

-0.15

jah

-0.14

á»«ng

-0.14

essian

-0.14

ESC

-0.13

soon

-0.13

enor

-0.13

ÅĦ

-0.13

ature

-0.13

POSITIVE LOGITS

ayah

0.19

Pur

0.18

pur

0.16

etest

0.16

eph

0.15

okus

0.15

isos

0.14

hetic

0.14

pur

0.14

roz

0.14

Activations Density 0.004%

mentions or discussions of prejudice and discrimination

No Comments

No Known Activations