INDEX

Explanations

keywords related to numerical data or quantifiable elements

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

eral

-0.15

enser

-0.15

achu

-0.15

OLA

-0.14

THON

-0.14

yre

-0.14

Ã¶k

-0.13

asers

-0.13

POSITIVE LOGITS

istrovstvÃŃ

0.15

 Meredith

0.14

 Fleming

0.14

 Tobias

0.14

codegen

0.13

ughter

0.13

 RedirectTo

0.13

à¥įà¤¬à¤¨

0.13

èĸ¦

0.13

fono

0.13

Activations Density 0.037%

keywords related to numerical data or quantifiable elements

No Comments

No Known Activations