INDEX

Explanations

references to measurements of length or dimensions

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

etat

-0.15

MOOTH

-0.15

uien

-0.15

ÅĽ

-0.14

loff

-0.14

ä»¶

-0.14

er

-0.14

_EMIT

-0.13

regunta

-0.13

ìĥī

-0.13

POSITIVE LOGITS

wise

0.26

ened

0.22

=length

0.20

ening

0.19

less

0.19

lessness

0.18

ronics

0.17

ake

0.17

/type

0.16

leftright

0.16

Activations Density 0.058%

references to measurements of length or dimensions

No Comments

No Known Activations