INDEX

Explanations

references to media content, particularly videos and interviews

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

 viewer

-0.16

 Viewer

-0.15

ÙĨØ§ÙħÙĩ

-0.15

 viewers

-0.14

andin

-0.14

metatable

-0.14

Ð¾ÑĪ

-0.14

akin

-0.14

 content

-0.14

ird

-0.14

POSITIVE LOGITS

embed

0.24

 embed

0.23

 embedded

0.23

_embed

0.23

.embed

0.22

 Embed

0.22

 below

0.21

embedding

0.21

Embed

0.21

 embedding

0.21

Activations Density 0.074%

references to media content, particularly videos and interviews

No Comments

No Known Activations