INDEX

Explanations

instances of the word "on" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÑĢÐµÐ´Ð¸ÑĤ

-0.16

anlar

-0.14

alous

-0.14

CUS

-0.14

 Beit

-0.13

credits

-0.13

åĪ¥

-0.13

raki

-0.13

Ã²i

-0.13

 institution

-0.13

POSITIVE LOGITS

ÐµÑĢÐº

0.16

olis

0.16

heim

0.15

ignet

0.15

esp

0.15

 Kens

0.15

chestra

0.14

gang

0.14

erk

0.14

Activations Density 0.251%

instances of the word "on" in various contexts

No Comments

No Known Activations