INDEX

Explanations

governmental or political district representations and designations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 lean

-0.16

icolor

-0.15

IGINAL

-0.15

Ø§Ø¨

-0.15

etten

-0.15

crest

-0.14

uien

-0.14

@student

-0.14

elin

-0.14

aeda

-0.14

POSITIVE LOGITS

 representation

0.18

representation

0.15

 hust

0.15

0.14

 tougher

0.13

 Ð¿ÑĢÐµÐ´ÑģÑĤÐ°Ð²

0.13

 actionTypes

0.13

owie

0.13

acht

0.13

mens

0.13

Activations Density 0.022%

governmental or political district representations and designations

No Comments

No Known Activations