INDEX

Explanations

punctuation marks, particularly parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

odi

-0.16

lesia

-0.15

erville

-0.15

oni

-0.14

erson

-0.14

ENDER

-0.14

enti

-0.14

chers

-0.14

OLEAN

-0.14

encion

-0.14

POSITIVE LOGITS

ziej

0.17

ãĤ¤ãĥ³ãĥĪ

0.17

tem

0.16

roz

0.16

/lg

0.16

andReturn

0.14

DTD

0.14

hem

0.13

roll

0.13

 Platz

0.13

Activations Density 0.019%

punctuation marks, particularly parentheses

No Comments

No Known Activations