INDEX

Explanations

references to programming and import statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ango

-0.16

YW

-0.15

loquent

-0.14

utz

-0.14

 Berm

-0.14

erk

-0.14

iÃªn

-0.14

TEMPL

-0.14

POSITIVE LOGITS

.synthetic

0.16

chia

0.16

ãĤ¦ãĤ¹

0.15

_amp

0.15

ignon

0.15

WindowTitle

0.14

orrent

0.14

_SIGNATURE

0.14

 Leban

0.14

(success

0.14

Activations Density 0.002%

references to programming and import statements

No Comments

No Known Activations