INDEX

Explanations

proper nouns or names, particularly those related to places, people, or significant entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

inx

-0.15

 operator

-0.14

iggins

-0.14

angkan

-0.14

igger

-0.14

Ð°ÑĤÐµÐ³

-0.14

HUD

-0.14

ãĤ

-0.14

ventus

-0.14

ucus

-0.14

POSITIVE LOGITS

otten

0.15

hetto

0.15

mez

0.14

 misunder

0.14

pta

0.14

 maduras

0.14

ichte

0.13

finger

0.13

 Heck

0.13

mund

0.13

Activations Density 0.129%

proper nouns or names, particularly those related to places, people, or significant entities

No Comments

No Known Activations