INDEX

Explanations

occurrences of the word "Berg" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

er

-0.19

rsa

-0.17

etri

-0.15

curity

-0.15

rs

-0.15

tt

-0.15

eru

-0.15

rise

-0.14

pieces

-0.14

POSITIVE LOGITS

amo

0.21

antino

0.21

amas

0.20

undy

0.20

anza

0.19

doll

0.18

dorf

0.17

thora

0.17

ersen

0.17

elson

0.16

Activations Density 0.007%

occurrences of the word "Berg" in various contexts

No Comments

No Known Activations