INDEX

Explanations

references to capacity and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ardon

-0.20

oram

-0.16

linger

-0.16

.LookAndFeel

-0.15

iana

-0.15

é»İ

-0.15

ollo

-0.15

edy

-0.14

ppo

-0.14

HEST

-0.14

POSITIVE LOGITS

esser

0.17

cing

0.15

agos

0.15

à¥Ģà¤¯

0.14

sag

0.14

gt

0.14

wise

0.14

ta

0.14

 reife

0.14

eing

0.14

Activations Density 0.015%

references to capacity and its variations in context

No Comments

No Known Activations