INDEX

Explanations

names and brand identifiers in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

yz

-0.15

 ÂłÂł ÂłÂł

-0.14

flen

-0.14

ÑĢÑĥÐº

-0.14

Å¡t

-0.14

à¸µà¸¢à¸ģ

-0.14

ucher

-0.14

andra

-0.14

bert

-0.13

POSITIVE LOGITS

(Component

0.15

æĽ

0.15

 derog

0.14

—

0.14

 Preston

0.13

nota

0.13

ACHED

0.13

orne

0.13

Enlarge

0.13

Activations Density 0.238%

names and brand identifiers in the text

No Comments

No Known Activations