INDEX

Explanations

details related to physical locations and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

strup

-0.16

bie

-0.15

ÑĨÑı

-0.15

èĦ

-0.14

 Ø§ÙĦØµÙģ

-0.14

ãĥĵãĥ¼

-0.13

_fa

-0.13

Ð½Ð¾Ð·

-0.13

_HTML

-0.13

shint

-0.13

POSITIVE LOGITS

 ÑģÑĤÐ°ÑĢÐ¸

0.17

ÏĨÎ¹

0.15

getApplication

0.15

mgr

0.15

elu

0.14

Ø³ØªØ§ÙĨÛĮ

0.14

Ĥæķ°

0.14

Â©Â©

0.14

.uf

0.13

Activations Density 0.081%

details related to physical locations and structures

No Comments

No Known Activations