INDEX

Explanations

occurrences of the word "sub" in various contexts, often related to positions or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

dech

-0.18

Ã§o

-0.18

mland

-0.16

uese

-0.16

andr

-0.15

HITE

-0.15

aped

-0.14

inz

-0.14

plorer

-0.14

Ð»Ð¸Ð¶

-0.14

POSITIVE LOGITS

sequent

0.28

cribe

0.27

scribers

0.27

scri

0.27

tle

0.26

stitution

0.26

lime

0.26

stit

0.25

stitutions

0.25

sid

0.25

Activations Density 0.014%

occurrences of the word "sub" in various contexts, often related to positions or roles

No Comments

No Known Activations