INDEX

Explanations

specific formatting and punctuation used in coding or technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ternal

-0.18

amin

-0.17

 TMPro

-0.17

bil

-0.15

 Eternal

-0.15

gebung

-0.15

(nd

-0.14

 Ð¿ÑĢÐ¸ÐµÐ¼

-0.14

alars

-0.14

IID

-0.14

POSITIVE LOGITS

Ã¶m

0.16

çĿ

0.16

hyp

0.15

von

0.15

aker

0.15

nett

0.15

ais

0.15

ouse

0.15

 Publisher

0.14

Activations Density 0.021%

specific formatting and punctuation used in coding or technical documentation

No Comments

No Known Activations