INDEX

Explanations

keywords related to prominent names and brands

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

 Reserved

-0.17

Oak

-0.14

cimal

-0.13

apis

-0.13

·

-0.13

igg

-0.13

 reserved

-0.13

coh

-0.12

elen

-0.12

 çĨ

-0.12

POSITIVE LOGITS

ebek

0.17

_deep

0.15

owie

0.15

kick

0.14

ÐµÑĢÐ¿

0.14

ussen

0.14

alie

0.14

ERRU

0.13

ailer

0.13

senha

0.13

Activations Density 0.104%

keywords related to prominent names and brands

No Comments

No Known Activations