INDEX

Explanations

numerical or time-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

US

-0.20

æĹıèĩªæ²»

-0.16

US

-0.14

 nonzero

-0.14

edException

-0.14

isse

-0.14

\\.

-0.14

\.

-0.14

 Ð²Ð´

-0.14

iera

-0.13

POSITIVE LOGITS

deniz

0.15

RIES

0.15

lero

0.14

-Encoding

0.14

ONENT

0.14

.free

0.13

/Input

0.13

Gry

0.13

cly

0.13

akin

0.13

Activations Density 0.042%

numerical or time-related information

No Comments

No Known Activations