INDEX

Explanations

mathematical or structural notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ãĥ³ãĥĳ

-0.14

ATS

-0.14

endar

-0.14

pei

-0.14

rott

-0.13

vrier

-0.13

inc

-0.13

POSITIVE LOGITS

 Shea

0.17

äºĭæĥħ

0.15

>{!!

0.15

antan

0.14

urnished

0.14

icted

0.14

icensed

0.14

 pairs

0.14

_canvas

0.13

ackbar

0.13

Activations Density 0.097%

mathematical or structural notations

No Comments

No Known Activations