INDEX

Explanations

phrases indicating the existence or presence of objects, situations, or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ãĥ³ãĥĩãĤ£

-0.16

ãĥ³ãĤ¸

-0.15

Ð¾ÑĢÐ¾Ð´

-0.14

egra

-0.14

ubi

-0.14

TickCount

-0.14

orthy

-0.13

allet

-0.13

 VerfÃ¼gung

-0.13

.mongo

-0.13

POSITIVE LOGITS

 certain

0.17

 ways

0.15

ertain

0.15

ÑĤÑĢÐ°

0.15

Jad

0.15

Certain

0.15

ĥn

0.14

 Certain

0.14

ofi

0.14

benef

0.14

Activations Density 0.091%

phrases indicating the existence or presence of objects, situations, or conditions

No Comments

No Known Activations