INDEX

Explanations

concepts related to value and meaningful experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

irit

-0.16

upa

-0.16

ored

-0.15

ien

-0.15

irl

-0.15

xit

-0.15

ë²Ī

-0.14

utsch

-0.14

illa

-0.13

ihad

-0.13

POSITIVE LOGITS

ults

0.15

0.14

-cols

0.14

orns

0.14

fal

0.14

Ã¡nu

0.14

ipment

0.14

lux

0.14

Î³Î³ÏģÎ±ÏĨ

0.13

 chamber

0.13

Activations Density 0.544%

concepts related to value and meaningful experiences

No Comments

No Known Activations