INDEX

Explanations

numerical identifiers and references, typically related to programming or technical documentation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Shed

-0.15

_UNUSED

-0.14

tip

-0.14

inion

-0.14

por

-0.14

EMA

-0.14

erness

-0.13

.Enqueue

-0.13

ohl

-0.13

.Unity

-0.13

POSITIVE LOGITS

ë¥ĺ

0.16

į

0.16

lsen

0.15

rita

0.15

azer

0.14

chi

0.14

igham

0.14

ì¦Ŀ

0.14

ings

0.14

olle

0.14

Activations Density 0.018%

numerical identifiers and references, typically related to programming or technical documentation

No Comments

No Known Activations