INDEX

Explanations

textual structure and section headings in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

zel

-0.16

Ã©r

-0.15

lds

-0.15

 Rudd

-0.14

istes

-0.14

atts

-0.14

aton

-0.14

ardon

-0.14

dit

-0.13

POSITIVE LOGITS

.elapsed

0.15

oftware

0.15

å¤§åĪ©

0.14

loub

0.14

edn

0.14

Î´Î¹Î¿

0.14

LOCKS

0.13

pheric

0.13

_SA

0.12

 vrch

0.12

Activations Density 0.002%

textual structure and section headings in documents

No Comments

No Known Activations