INDEX

Explanations

references to loudness or loud sounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

idar

-0.17

AZE

-0.15

azio

-0.15

iles

-0.15

ooled

-0.15

ëł¨

-0.15

byt

-0.15

 å¤§éĺª

-0.14

ameron

-0.14

ilig

-0.14

POSITIVE LOGITS

speaker

0.26

spe

0.20

mouth

0.19

arde

0.18

lier

0.16

oun

0.15

ache

0.15

-mouth

0.14

TEMPL

0.14

owler

0.14

Activations Density 0.020%

references to loudness or loud sounds

No Comments

No Known Activations