INDEX

Explanations

references to events, projects, or discussions within a formal or corporate context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ÂŃ

-0.16

hee

-0.14

[_

-0.14

 Straw

-0.13

ï»¿↵↵

-0.13

[*

-0.13

StackNavigator

-0.13

[](

-0.13

Âł↵

-0.12

[]↵

-0.12

POSITIVE LOGITS

ãĢĤ↵↵↵↵↵↵

0.20

itemap

0.16

xes

0.14

GuidId

0.14

edir

0.13

ï¼ļ"

0.13

multipart

0.13

icari

0.12

Ø³Ø§ÙĨÛĮ

0.12

.$$

0.12

Activations Density 3.966%

references to events, projects, or discussions within a formal or corporate context

No Comments

No Known Activations