INDEX

Explanations

instances of the word "ra" and its variations, indicating a focus on repeated syllables or sounds

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

cta

-0.19

irma

-0.19

chia

-0.19

ä¸īçº§

-0.17

aira

-0.16

razil

-0.14

iron

-0.14

arrant

-0.14

Î¹Ïĥ

-0.13

aidu

-0.13

POSITIVE LOGITS

er

0.20

odon

0.16

linger

0.16

onde

0.15

arth

0.15

lest

0.15

eof

0.14

wert

0.14

ZY

0.14

Activations Density 0.033%

instances of the word "ra" and its variations, indicating a focus on repeated syllables or sounds

No Comments

No Known Activations