INDEX

Explanations

key identifiers related to formal communication or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 bart

-0.19

Bars

-0.16

 Bars

-0.16

bars

-0.15

 bars

-0.15

Unchecked

-0.15

-bars

-0.15

 Bart

-0.15

pau

-0.14

 ÑĢÐ°Ð¼

-0.14

POSITIVE LOGITS

ç¼

0.17

isson

0.16

ussed

0.16

ç·ł

0.15

breadcrumb

0.14

tero

0.14

teri

0.14

imbus

0.14

affe

0.14

assin

0.14

Activations Density 0.002%

key identifiers related to formal communication or documentation

No Comments

No Known Activations