INDEX

Explanations

numerical values and comments, often associated with measurements or statistics

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

bell

-0.16

Flo

-0.16

iton

-0.15

 Diet

-0.14

ushman

-0.14

 Predictor

-0.14

Ð¼Ð°Ð³

-0.14

 ÑģÑĤÐ°Ð½Ð¾Ð²

-0.14

raid

-0.13

kil

-0.13

POSITIVE LOGITS

isure

0.17

ĥn

0.15

|_|

0.14

 replies

0.14

uba

0.14

æĪª

0.14

 Hiro

0.13

anship

0.13

iman

0.13

bur

0.13

Activations Density 0.041%

numerical values and comments, often associated with measurements or statistics

No Comments

No Known Activations

numerical values and comments, often associated with measurements or statistics

No Comments

No Known Activations