INDEX

Explanations

printed materials or printed resources related to health information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Hra

-0.15

apter

-0.15

apus

-0.14

ruit

-0.14

ersistent

-0.14

OX

-0.14

istrat

-0.14

Ð¾Ð²ÐµÑĢ

-0.13

é¡

-0.13

tere

-0.13

POSITIVE LOGITS

0.16

 resp

0.16

0.15

abbr

0.15

0.14

aidu

0.14

Activations Density 0.113%

printed materials or printed resources related to health information

No Comments

No Known Activations

printed materials or printed resources related to health information

No Comments

No Known Activations