INDEX

Explanations

references to quantities and numbers in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 ours

-0.16

ert

-0.15

zc

-0.15

ichel

-0.15

elmet

-0.14

iment

-0.14

FromArray

-0.14

ists

-0.14

atra

-0.14

POSITIVE LOGITS

.sdk

0.16

ivatel

0.15

 prostitut

0.15

aviour

0.14

Bulk

0.14

_flux

0.14

cona

0.14

aval

0.14

 everyone

0.14

indow

0.14

Activations Density 0.002%

references to quantities and numbers in a variety of contexts

No Comments

No Known Activations