INDEX

Explanations

sequences and patterns in numeric codes or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

lut

-0.17

-ever

-0.17

()

-0.15

avig

-0.14

lue

-0.14

ibbon

-0.14

ano

-0.13

 scrape

-0.13

ringe

-0.13

QR

-0.13

POSITIVE LOGITS

 Ð¿Ð¾Ð´Ñģ

0.15

Ã¡cil

0.14

akter

0.14

ernote

0.14

anford

0.14

ä»¬

0.13

ÙĬØ§Øª

0.13

chandle

0.13

arts

0.13

Activations Density 0.010%

sequences and patterns in numeric codes or symbols

No Comments

No Known Activations