INDEX

Explanations

specific phonetic patterns in words, particularly those containing "iph," "aim," and "app."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

çµ

-0.15

ABS

-0.15

Ub

-0.15

alc

-0.15

urette

-0.14

aton

-0.14

ieber

-0.14

Ã©v

-0.14

deniz

-0.14

 concent

-0.14

POSITIVE LOGITS

atchewan

0.22

.amazonaws

0.17

-serif

0.16

Vectorizer

0.15

oÄŁ

0.15

Mask

0.15

çŃĭ

0.15

ãĥ«ãĥĪ

0.14

 Scenes

0.14

imus

0.14

Activations Density 0.099%

specific phonetic patterns in words, particularly those containing "iph," "aim," and "app."

No Comments

No Known Activations