INDEX

Explanations

conversational expressions related to social interactions and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ð¼ÐµÑĩ

-0.15

Ìģ

-0.15

rc

-0.13

è¾ĥ

-0.13

ymoon

-0.13

ÑıÐ²

-0.13

å¡ļ

-0.12

 Ø«Ø§Ø¨Øª

-0.12

IENTATION

-0.12

INY

-0.12

POSITIVE LOGITS

 yeah

0.15

apos

0.15

 Yeah

0.14

mr

0.14

ÃŃses

0.14

And

0.13

yes

0.13

ikit

0.13

Activations Density 0.057%

conversational expressions related to social interactions and evaluations

No Comments

No Known Activations