INDEX

Explanations

specific instructions or conditions related to rules and parameters in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ð¸ÑĤÐ¾ÑĢ

-0.16

ÑıÑĩ

-0.15

åĲ§

-0.14

 repmat

-0.13

á»Ń

-0.13

conti

-0.13

iges

-0.12

ĥĿ

-0.12

 newIndex

-0.12

ikip

-0.12

POSITIVE LOGITS

 exactly

1.30

 exact

1.30

 precisely

1.16

exact

1.04

 Exactly

1.02

 Exact

1.01

 precise

0.96

Exactly

0.96

Exact

0.94

_exact

0.83

Activations Density 0.521%

specific instructions or conditions related to rules and parameters in various contexts

No Comments

No Known Activations