INDEX

Explanations

instances of the letter 'f' 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

iska

-0.18

ade

-0.17

formed

-0.17

ero

-0.15

fav

-0.15

lined

-0.15

ruta

-0.14

era

-0.14

 Restoration

-0.14

tero

-0.14

POSITIVE LOGITS

ocaly

0.16

omor

0.15

rena

0.15

bidden

0.14

andre

0.14

áº¾

0.14

 miÃªu

0.14

ibaba

0.14

ToProps

0.14

teenth

0.14

Activations Density 0.101%

instances of the letter 'f' in various contexts

No Comments

No Known Activations