INDEX

Explanations

references to specific years, particularly in the mid-20th century

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

enders

-0.17

itzer

-0.16

aying

-0.16

ailing

-0.16

avaÅŁ

-0.15

ender

-0.15

pton

-0.15

acular

-0.15

inders

-0.14

 Excell

-0.14

POSITIVE LOGITS

alk

0.16

º

0.15

ãĥ¥ãĥ¼

0.15

çĶ

0.14

eshire

0.14

ard

0.14

erry

0.14

mort

0.14

icks

0.14

Activations Density 0.009%

references to specific years, particularly in the mid-20th century

No Comments

No Known Activations