INDEX

Explanations

various applications and features related to tools and resources

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

ignite

-0.15

abei

-0.14

 strengthened

-0.14

unsch

-0.13

ault

-0.13

igner

-0.13

ãĤ¶ãĥ¼

-0.13

LEAN

-0.13

izmet

-0.12

atem

-0.12

POSITIVE LOGITS

 allow

0.85

 allows

0.81

 allowing

0.77

allow

0.77

allows

0.70

 enable

0.68

åħģ

0.68

 permet

0.68

 Allow

0.68

Allow

0.68

Activations Density 0.815%

various applications and features related to tools and resources

No Comments

No Known Activations