INDEX

Explanations

textual elements associated with formatting or structure in source code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

acos

-0.17

yles

-0.15

ãĥŃãĥ³

-0.14

antal

-0.14

åĸ¶

-0.14

rophe

-0.14

 ofType

-0.14

ampo

-0.14

DEV

-0.14

POSITIVE LOGITS

ÑĨÐµÐ½

0.17

int

0.16

oth

0.15

edik

0.15

elines

0.14

.jp

0.14

olean

0.14

 Borg

0.14

Activations Density 0.142%

textual elements associated with formatting or structure in source code

No Comments

No Known Activations