INDEX

Explanations

instances of the word "match" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

LU

-0.18

LU

-0.17

unf

-0.15

zin

-0.15

tog

-0.14

 Cant

-0.14

oston

-0.13

ju

-0.13

 meaning

-0.13

aso

-0.13

POSITIVE LOGITS

OfSize

0.19

ively

0.17

kus

0.16

olation

0.15

andise

0.15

ron

0.14

ingly

0.14

elerik

0.14

etty

0.14

DispatchToProps

0.14

Activations Density 0.035%

instances of the word "match" in various contexts

No Comments

No Known Activations