INDEX

Explanations

occurrences of the term "google" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Merry

-0.16

 Cornell

-0.15

nul

-0.15

ÐµÐ»ÐµÑĦ

-0.15

uzzi

-0.15

ÑĨÐµÑĢ

-0.14

ppt

-0.14

ingo

-0.14

ils

-0.14

gressor

-0.14

POSITIVE LOGITS

feld

0.15

endon

0.14

 Ã¥r

0.14

:nth

0.14

chai

0.14

 sÃŃ

0.14

 filetype

0.13

aviors

0.13

rias

0.13

Activations Density 0.004%

occurrences of the term "google" in various contexts

No Comments

No Known Activations