INDEX

Explanations

actions involving the word "bend" and its variations in different contexts

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

cept

-0.20

interop

-0.18

quia

-0.17

uem

-0.17

ãĥ¼ãĥľ

-0.16

ivant

-0.15

erap

-0.15

bourg

-0.14

bero

-0.14

nown

-0.14

POSITIVE LOGITS

 Bend

0.24

 bending

0.22

 bend

0.22

 bent

0.20

/stretch

0.19

 bends

0.18

ych

0.17

ekli

0.17

Activations Density 0.019%

actions involving the word "bend" and its variations in different contexts

No Comments

No Known Activations