INDEX

Explanations

interrogative phrases that inquire about how to perform specific actions or tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.URI

-0.14

cke

-0.14

quina

-0.14

adi

-0.14

-thumbnails

-0.14

pop

-0.14

essaging

-0.14

strup

-0.14

UPPORTED

-0.14

Queries

-0.14

POSITIVE LOGITS

ief

0.15

lyph

0.14

 cÃ¢n

0.14

ats

0.14

ihil

0.14

ustr

0.13

ys

0.13

Activations Density 0.019%

interrogative phrases that inquire about how to perform specific actions or tasks

No Comments

No Known Activations