INDEX

Explanations

occurrences of the word "brief" and its variations, indicating a focus on concise summaries or discussions

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

ombo

-0.18

hlen

-0.17

ais

-0.16

vil

-0.15

al

-0.15

arios

-0.15

iggs

-0.14

upro

-0.14

ãģ°

-0.14

icana

-0.14

POSITIVE LOGITS

case

0.36

ings

0.29

cases

0.26

est

0.24

ly

0.21

ening

0.20

ingly

0.20

ness

0.20

ens

0.19

Ļ¨

0.18

Activations Density 0.014%

occurrences of the word "brief" and its variations, indicating a focus on concise summaries or discussions

No Comments

No Known Activations