INDEX

Explanations

names and terms related to specific brands or entities in the entertainment and service industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ovit

-0.18

ovice

-0.16

VRT

-0.15

eel

-0.15

igne

-0.14

icine

-0.14

Hang

-0.14

IP

-0.14

êµ°

-0.14

POSITIVE LOGITS

à¤¾à¤¯à¤¤

0.20

eyJ

0.17

ual

0.16

ardless

0.16

ually

0.16

annon

0.16

ardo

0.15

pressions

0.15

kehr

0.15

ascimento

0.15

Activations Density 0.032%

names and terms related to specific brands or entities in the entertainment and service industries

No Comments

No Known Activations