INDEX

Explanations

instructions related to data handling and processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

cion

-0.16

izu

-0.16

rowable

-0.15

achuset

-0.14

bz

-0.14

onet

-0.14

Ð»ÑĥÑĪ

-0.14

arya

-0.13

izzas

-0.13

ivent

-0.13

POSITIVE LOGITS

 paste

0.49

 Paste

0.44

 copy

0.43

paste

0.43

 clipboard

0.41

 Copy

0.41

 copied

0.41

Paste

0.40

-copy

0.39

 copying

0.39

Activations Density 0.042%

instructions related to data handling and processing

No Comments

No Known Activations