INDEX

Explanations

the word "except" and its variations, indicating exclusions or exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

coni

-0.21

kir

-0.15

kola

-0.14

ause

-0.14

izza

-0.14

 Lair

-0.14

FIX

-0.14

ftar

-0.14

POSITIVE LOGITS

ing

0.37

ting

0.19

ING

0.19

0.17

ed

0.17

ingly

0.16

reme

0.15

antly

0.15

edException

0.15

eur

0.15

Activations Density 0.011%

the word "except" and its variations, indicating exclusions or exceptions

No Comments

No Known Activations