INDEX

Explanations

derogatory or obscene language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

sou

-0.17

ists

-0.16

ign

-0.16

borg

-0.14

onder

-0.14

imers

-0.14

argins

-0.14

iom

-0.14

zet

-0.14

POSITIVE LOGITS

assic

0.15

IFO

0.15

 anale

0.14

ãĦ

0.14

rgan

0.14

nop

0.14

gis

0.14

PTS

0.14

aukee

0.13

anske

0.13

Activations Density 0.060%

derogatory or obscene language

No Comments

No Known Activations