INDEX

Explanations

concepts related to aspiration and expectation

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

isman

-0.15

anson

-0.15

 PureComponent

-0.15

SEQ

-0.15

 Barton

-0.14

ITUDE

-0.14

Ã©ro

-0.13

tro

-0.13

Ø§Ø¬

-0.13

itude

-0.13

POSITIVE LOGITS

sembled

0.16

 happening

0.15

æĺ¯ä¸Ģä¸ª

0.14

eyh

0.13

å°ĸ

0.13

ccess

0.13

eson

0.13

inem

0.13

afone

0.13

Activations Density 0.043%

concepts related to aspiration and expectation

No Comments

No Known Activations