INDEX

Explanations

references to images and their copyright details

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

onic

-0.16

fang

-0.15

orro

-0.15

ÙĪØ§Ø±Ùĩ

-0.15

edList

-0.15

Î¿Î»

-0.14

 Ø§ÙĦØ¨ÙĦØ¯

-0.14

 reform

-0.13

_COMMON

-0.13

logue

-0.13

POSITIVE LOGITS

nila

0.17

æĻ

0.15

 âĹĦ

0.15

nil

0.15

Å¯l

0.14

ÅĻel

0.14

argout

0.14

ToBounds

0.14

Activations Density 0.025%

references to images and their copyright details

No Comments

No Known Activations