INDEX

Explanations

timestamps and durations in a context related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

markup

-0.16

aea

-0.14

%d

-0.14

 ì¡

-0.14

 Pandora

-0.13

/gin

-0.13

 nghá»ĭ

-0.13

Paused

-0.13

jac

-0.13

acket

-0.13

POSITIVE LOGITS

unist

0.16

spin

0.15

ottes

0.15

IM

0.14

eson

0.14

icrous

0.14

 spin

0.14

ä»Ĭ

0.14

conds

0.14

 Spin

0.14

Activations Density 0.004%

timestamps and durations in a context related to events

No Comments

No Known Activations