INDEX

Explanations

instances of verbs and specific phrases indicating actions or requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

TABLE

-0.16

/cop

-0.16

essel

-0.15

 TRACE

-0.15

astreet

-0.15

atter

-0.15

ÂłPS

-0.15

/Table

-0.14

 settling

-0.14

ATTER

-0.14

POSITIVE LOGITS

 Notice

0.16

uds

0.15

 haven

0.15

Rud

0.15

 noticed

0.15

 notice

0.15

Notice

0.14

ctp

0.13

 noticing

0.13

 Bank

0.13

Activations Density 0.017%

instances of verbs and specific phrases indicating actions or requests

No Comments

No Known Activations