INDEX

Explanations

references to the term "Hob" or related variations, indicating a focus on a specific topic or entity associated with that name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 desar

-0.15

AdapterFactory

-0.15

Ð»ÑĥÑĪ

-0.15

 costa

-0.15

 envelope

-0.15

ictor

-0.14

ë¹Ļ

-0.14

ows

-0.14

pour

-0.14

Ð»ÑĥÐ³Ð¸

-0.14

POSITIVE LOGITS

OKEN

0.21

oken

0.19

nob

0.19

sonian

0.18

Hob

0.18

bie

0.17

bs

0.17

Nob

0.17

annes

0.16

son

0.16

Activations Density 0.005%

references to the term "Hob" or related variations, indicating a focus on a specific topic or entity associated with that name

No Comments

No Known Activations