INDEX

Explanations

references to specific years and events related to culture and society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

utherford

-0.15

 obvious

-0.15

ÏĥÏĦÎ±

-0.14

 prot

-0.14

agh

-0.14

oldem

-0.14

nde

-0.13

iegel

-0.13

 æĽ

-0.13

ooky

-0.13

POSITIVE LOGITS

tent

0.16

ittle

0.16

kili

0.15

gb

0.15

asma

0.15

jar

0.14

cre

0.14

 Lama

0.13

ipay

0.13

iar

0.13

Activations Density 0.071%

references to specific years and events related to culture and society

No Comments

No Known Activations