INDEX

Explanations

XML attributes or specifications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

illa

-0.18

-0.17

-0.16

arde

-0.16

itals

-0.16

Ã´ng

-0.16

ores

-0.15

traits

-0.14

POSITIVE LOGITS

aison

0.14

vrier

0.14

ajor

0.14

ÐµÐºÑĤÑĥ

0.14

bras

0.14

/MIT

0.14

ihan

0.14

PD

0.14

ld

0.13

ECH

0.13

Activations Density 0.002%

XML attributes or specifications in various contexts

No Comments

No Known Activations