INDEX

Explanations

instances of the letter 'e' 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 otherwise

-0.17

 Bench

-0.16

essen

-0.15

 OTHERWISE

-0.15

ibi

-0.13

IRE

-0.13

 Perr

-0.13

otine

-0.13

rites

-0.13

 fold

-0.13

POSITIVE LOGITS

adow

0.17

uger

0.15

orning

0.14

euillez

0.14

ãĥ©ãĤ¤

0.14

 ë°ĶëĿ¼

0.14

 Hastings

0.13

 Wilkinson

0.13

ķĮ

0.13

lington

0.13

Activations Density 0.007%

instances of the letter 'e' in various contexts

No Comments

No Known Activations