INDEX

Explanations

references to key individuals and events in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

deniz

-0.15

iland

-0.15

orado

-0.14

_processors

-0.14

utzer

-0.14

jes

-0.14

 Reconstruction

-0.14

_FC

-0.14

abelle

-0.13

POSITIVE LOGITS

 Soviet

0.36

 Cold

0.35

 communist

0.28

Cold

0.28

 East

0.28

 Communist

0.27

 communism

0.27

 Soviets

0.26

 USSR

0.25

 ÑĢÐ°Ð´ÑıÐ½

0.25

Activations Density 0.117%

references to key individuals and events in historical contexts

No Comments

No Known Activations