INDEX

Explanations

terms related to entertainment and content production

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-ÑĤÐ¾

-0.15

itu

-0.14

 Pant

-0.14

ensitive

-0.14

rames

-0.14

st

-0.14

Ã³b

-0.14

inea

-0.13

isen

-0.13

ston

-0.13

POSITIVE LOGITS

hlas

0.16

.modelo

0.15

-fontawesome

0.15

edImage

0.15

ìĻ

0.14

essian

0.14

olle

0.14

ault

0.14

hole

0.14

orca

0.14

Activations Density 0.000%

terms related to entertainment and content production

No Comments

No Known Activations