INDEX

Explanations

references to the roles individuals or groups play within various contexts

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

å°ĳå¥³

-0.15

adera

-0.15

èĭĹ

-0.15

rani

-0.15

ugin

-0.14

á»ĳ

-0.14

ilor

-0.13

ople

-0.13

ivor

-0.13

POSITIVE LOGITS

 shaping

0.19

 overall

0.19

 Overall

0.17

iece

0.16

Overall

0.16

 society

0.15

overall

0.15

llen

0.14

 developments

0.14

 relation

0.14

Activations Density 0.082%

references to the roles individuals or groups play within various contexts

No Comments

No Known Activations