INDEX

Explanations

technical terms and code-related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

cke

-0.17

BITS

-0.16

 moons

-0.15

ÏĩÏī

-0.15

 Kerr

-0.14

swire

-0.14

bersome

-0.14

uncate

-0.14

ammen

-0.14

 Bakan

-0.14

POSITIVE LOGITS

 xmlns

0.18

lay

0.18

.addView

0.15

 orientation

0.15

/widget

0.15

bah

0.15

Ð½Ð¾ÑĪ

0.14

 patter

0.14

[assembly

0.14

alog

0.14

Activations Density 0.013%

technical terms and code-related elements

No Comments

No Known Activations