INDEX

Explanations

specific names of individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ucht

-0.16

adla

-0.16

pollo

-0.16

autoload

-0.15

ÑĢÐ¾Ñĩ

-0.15

Calibri

-0.15

estone

-0.15

stm

-0.14

andest

-0.14

Ð»Ð°Ñĩ

-0.14

POSITIVE LOGITS

bearing

0.15

 Priest

0.15

ose

0.15

ERIC

0.14

ÑĪÐ¾Ð²

0.14

 Martin

0.13

ton

0.13

Ð½Ð¾ÑĪ

0.13

ason

0.13

Activations Density 0.191%

specific names of individuals or entities

No Comments

No Known Activations