INDEX

Explanations

terms associated with ongoing activities 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 @ 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

avage

-0.16

tsky

-0.15

enti

-0.15

ibir

-0.15

ickle

-0.14

.GetType

-0.14

estroy

-0.14

ĴĪ

-0.14

oped

-0.14

turnstile

-0.14

POSITIVE LOGITS

0.16

 haul

0.15

é¨

0.14

ollah

0.14

oro

0.14

iser

0.13

Ø³ØªØ§ÙĨ

0.13

Ã¢n

0.13

 cuanto

0.13

oco

0.13

Activations Density 0.034%

terms associated with ongoing activities or events

No Comments

No Known Activations