INDEX

Explanations

instances of the word "repetitive" and its variations, indicating a focus on recurring actions or themes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ail

-0.15

rens

-0.15

ermen

-0.15

yster

-0.14

ect

-0.14

ister

-0.14

Strike

-0.14

 cong

-0.14

pain

-0.14

zik

-0.13

POSITIVE LOGITS

allet

0.19

/single

0.16

utherland

0.15

oins

0.15

dorf

0.15

_ARGUMENT

0.14

Īëĭ¤

0.14

deaux

0.14

ks

0.14

elt

0.14

Activations Density 0.021%

instances of the word "repetitive" and its variations, indicating a focus on recurring actions or themes

No Comments

No Known Activations