INDEX

Explanations

dialogue and expressions of emotions or actions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

irie

-0.16

orget

-0.14

 yourselves

-0.14

Fey

-0.14

ÅŁam

-0.14

 terminal

-0.14

 bump

-0.14

å°İ

-0.13

itez

-0.13

jl

-0.13

POSITIVE LOGITS

his

0.22

ä»ĸçļĦ

0.21

 himself

0.17

 yaptÄ±ÄŁÄ±

0.17

 seiner

0.16

his

0.16

ï¼Įä»ĸ

0.16

 jeho

0.15

 zijn

0.15

His

0.15

Activations Density 0.499%

dialogue and expressions of emotions or actions

No Known Activations