INDEX

Explanations

technical terms and code-related keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

à¸²à¸ļ

-0.15

 Levin

-0.15

raw

-0.15

 Jarvis

-0.15

ysz

-0.14

queeze

-0.14

ÑĤÐ°Ð¶

-0.14

.sz

-0.14

 Blur

-0.14

 blur

-0.14

POSITIVE LOGITS

.uml

0.23

ByExample

0.19

antine

0.18

tik

0.17

 diagrams

0.17

Pet

0.17

.metamodel

0.17

abb

0.17

modelName

0.16

èĢĹ

0.16

Activations Density 0.076%

technical terms and code-related keywords

No Comments

No Known Activations