INDEX

Explanations

phrases related to conflict and its avoidance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

aku

-0.16

/sdk

-0.15

 Dome

-0.15

oard

-0.15

azz

-0.14

Qed

-0.14

ÏĥÏĥ

-0.14

 Pear

-0.14

Î»Ïİ

-0.13

è½

-0.13

POSITIVE LOGITS

 Ether

0.15

 Franklin

0.15

bury

0.15

 King

0.15

illon

0.14

odon

0.14

 Spread

0.14

obus

0.14

ewan

0.14

Activations Density 0.089%

phrases related to conflict and its avoidance

No Comments

No Known Activations