INDEX

Explanations

phrases that express opinions or assessments about movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ublik

-0.15

¼åĲĪ

-0.14

agus

-0.14

Æ°

-0.14

odyn

-0.14

kir

-0.13

ropp

-0.13

 Ø¬Ø²

-0.13

Ø¬Ø²

-0.13

å¡ļ

-0.13

POSITIVE LOGITS

cf

0.15

 Ð´ÐµÐºÐ°

0.14

anki

0.14

enor

0.14

aurus

0.13

DEM

0.13

igm

0.13

Coins

0.13

iel

0.13

volatile

0.13

Activations Density 0.092%

phrases that express opinions or assessments about movies

No Comments

No Known Activations