INDEX

Explanations

instances of specific letter patterns or phonetic sounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

alte

-0.17

uchos

-0.15

ebi

-0.15

 sake

-0.15

uits

-0.14

ãģĹãĤĩ

-0.14

idental

-0.14

Ã¨s

-0.14

èĮ¨

-0.14

ftime

-0.14

POSITIVE LOGITS

lessly

0.20

fully

0.18

ALLY

0.17

mediately

0.16

ANNOT

0.16

0.15

Î»Î¹Î¬

0.15

 eldre

0.15

lear

0.15

ally

0.14

Activations Density 0.179%

instances of specific letter patterns or phonetic sounds

No Comments

No Known Activations