INDEX

Explanations

references to interactive learning experiences or workshops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

eed

-0.15

orre

-0.15

eck

-0.14

taj

-0.14

trag

-0.14

Ìī

-0.14

een

-0.14

 NavParams

-0.14

quam

-0.13

lad

-0.13

POSITIVE LOGITS

kop

0.16

ãĥ¬ãĥ³

0.14

Kah

0.13

/LICENSE

0.13

ipp

0.13

rena

0.13

 å®®

0.13

 áº¤

0.13

aphrag

0.13

steller

0.13

Activations Density 0.066%

references to interactive learning experiences or workshops

No Comments

No Known Activations