INDEX

Explanations

proper nouns, particularly names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 ÐŁÑĢÐ°

-0.16

iform

-0.14

ãĢĩ

-0.14

osto

-0.14

ãģıãĤĵ

-0.14

_formatter

-0.13

oris

-0.13

icom

-0.13

repid

-0.13

abwe

-0.13

POSITIVE LOGITS

AN

0.21

An

0.18

argv

0.16

ANN

0.15

ÑĶÐ½

0.15

 poster

0.15

 Annie

0.15

_AN

0.15

An

0.15

ä¸įå®ī

0.14

Activations Density 0.037%

proper nouns, particularly names and locations

No Comments

No Known Activations