INDEX

Explanations

the repetition of the word "in" across 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

favor

-0.15

nty

-0.15

 question

-0.15

é¤Ĭ

-0.15

enko

-0.15

acr

-0.14

ghan

-0.14

 Favor

-0.14

case

-0.14

.case

-0.14

POSITIVE LOGITS

 partnership

0.49

 cooperation

0.43

 collaboration

0.43

 association

0.39

 conjunction

0.35

association

0.32

partners

0.31

 Partnership

0.31

 combination

0.30

 affiliation

0.30

Activations Density 0.218%

the repetition of the word "in" across various contexts

No Comments

No Known Activations

the repetition of the word "in" across various contexts

No Comments

No Known Activations