INDEX

Explanations

numerical references or identifiers, particularly related to books and publications

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

umo

-0.17

 Lanka

-0.16

iÄħ

-0.15

 Stations

-0.14

egasus

-0.14

=cut

-0.14

eenth

-0.14

 SHARES

-0.14

issors

-0.14

POSITIVE LOGITS

st

0.18

 Gian

0.14

ming

0.14

edo

0.14

hest

0.13

 Freddie

0.13

ske

0.13

 aerial

0.13

ivers

0.13

Activations Density 0.386%

numerical references or identifiers, particularly related to books and publications

No Comments

No Known Activations