INDEX

Explanations

specific verbs and keywords associated with processes or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uming

-0.16

 Suff

-0.15

Vie

-0.14

Chocolate

-0.14

rine

-0.14

_SUITE

-0.14

åĪ©

-0.14

addock

-0.14

erea

-0.14

Ø·Ø§ÙĤ

-0.13

POSITIVE LOGITS

?url

0.20

oid

0.17

onaut

0.16

Pik

0.16

ober

0.15

ella

0.15

 Doll

0.14

 Budget

0.14

ÃŃn

0.14

/Typography

0.14

Activations Density 0.006%

specific verbs and keywords associated with processes or actions

No Comments

No Known Activations