INDEX

Explanations

terminology related to production and its status in a specific context, often regarding capacity or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

.eclipse

-0.16

ãģĭãģĳ

-0.15

æı

-0.15

olik

-0.14

 montage

-0.14

gar

-0.14

 Hath

-0.14

 participation

-0.14

wart

-0.14

quete

-0.14

POSITIVE LOGITS

uros

0.16

Nd

0.15

fect

0.14

 Sentry

0.14

eree

0.14

ÙĨØ³

0.14

0.13

ByExample

0.13

 ØªØ®

0.13

edly

0.13

Activations Density 0.288%

terminology related to production and its status in a specific context, often regarding capacity or events

No Comments

No Known Activations