INDEX

Explanations

references to specific individuals, places, or institutions in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

STRU

-0.16

itez

-0.16

 çĭ

-0.15

 voir

-0.15

 phÃ¡

-0.14

ÉĻ

-0.14

loh

-0.13

 frau

-0.13

ÐµÐ³

-0.13

icking

-0.13

POSITIVE LOGITS

ean

0.16

Animator

0.16

~-

0.15

uada

0.15

ston

0.15

olini

0.15

Ð¸Ð·Ð½ÐµÑģ

0.14

Ð¼Ð°Ð·

0.14

atsapp

0.14

Ã³mo

0.14

Activations Density 0.067%

references to specific individuals, places, or institutions in a narrative context

No Comments

No Known Activations