INDEX

Explanations

HTML anchor tags

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

cot

-0.15

dle

-0.15

 letterSpacing

-0.15

rott

-0.14

azor

-0.14

sons

-0.13

agascar

-0.13

ÑĥÑģÑĤÐ¸

-0.13

kus

-0.13

chez

-0.13

POSITIVE LOGITS

0.17

ameda

0.16

alc

0.15

ifar

0.14

opol

0.14

erÃ§

0.14

Uvs

0.14

¢

0.14

irket

0.14

mac

0.13

Activations Density 0.014%

HTML anchor tags

No Comments

No Known Activations