INDEX

Explanations

phrases indicating ongoing involvement or experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Inherits

-0.16

maal

-0.15

izer

-0.15

ÏĦÎŃ

-0.15

lingen

-0.15

IGIN

-0.15

 talented

-0.15

Bec

-0.14

erton

-0.14

 Mour

-0.14

POSITIVE LOGITS

 around

0.19

 Around

0.18

Around

0.18

 fixtures

0.18

 fixture

0.17

around

0.16

 providing

0.15

fixture

0.15

 integral

0.15

antics

0.15

Activations Density 0.049%

phrases indicating ongoing involvement or experience

No Comments

No Known Activations