INDEX

Explanations

references to specific train stations or station-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

tings

-0.18

entic

-0.17

lesh

-0.15

ÑĩÐ½Ñĸ

-0.15

UAL

-0.15

ustin

-0.15

cola

-0.15

ìĦł

-0.15

space

-0.15

acer

-0.15

POSITIVE LOGITS

nement

0.33

ery

0.31

ary

0.29

arity

0.28

wagon

0.23

naire

0.22

house

0.20

ality

0.19

aire

0.19

ARY

0.19

Activations Density 0.021%

references to specific train stations or station-related terms

No Comments

No Known Activations