INDEX

Explanations

geographical locations and names of television networks or shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ibir

-0.16

krom

-0.15

Ãµi

-0.14

quires

-0.14

à¥įà¤¸à¤°

-0.14

Çİ

-0.14

á»ĳn

-0.13

agara

-0.13

Ð´ÐµÑĢ

-0.13

ophon

-0.13

POSITIVE LOGITS

coni

0.15

jk

0.14

okoj

0.14

Marshal

0.14

atrix

0.14

ado

0.14

0.13

umbs

0.13

Activations Density 0.066%

geographical locations and names of television networks or shows

No Comments

No Known Activations