INDEX

Explanations

references to specific statistics, scores, or measurements related to performance or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ickerView

-0.16

Ð²Ð°Ð¶Ð°

-0.15

 Feder

-0.15

aeda

-0.15

mares

-0.15

YLON

-0.14

ummies

-0.14

reated

-0.14

_locator

-0.14

POSITIVE LOGITS

gh

0.17

æī

0.16

 centrif

0.14

{[

0.14

isle

0.14

hek

0.14

fos

0.13

 FIXME

0.13

 Curt

0.13

ctype

0.13

Activations Density 0.081%

references to specific statistics, scores, or measurements related to performance or outcomes

No Comments

No Known Activations