INDEX

Explanations

punctuation and formatting markers in mathematical expressions or equations

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

eus

-0.16

ERVER

-0.14

 slump

-0.14

ardon

-0.14

 Shed

-0.14

 Stir

-0.14

agrid

-0.14

hani

-0.14

Ã©r

-0.13

hev

-0.13

POSITIVE LOGITS

æ··

0.14

mojom

0.14

eren

0.14

ÙĦÙĥØªØ±

0.13

itech

0.13

 çĳ

0.13

 entreprene

0.13

sworth

0.13

median

0.13

contributors

0.13

Activations Density 0.044%

punctuation and formatting markers in mathematical expressions or equations

No Comments

No Known Activations