INDEX

Explanations

elements related to assignments and artistic projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ÑģÑĮ

-0.16

ellipsis

-0.15

-0.14

±

-0.14

quil

-0.14

Fra

-0.14

 Corpus

-0.14

ekte

-0.14

kip

-0.14

Clipboard

-0.14

POSITIVE LOGITS

 Incontri

0.15

èħ¾

0.15

iets

0.14

dÃ¼k

0.14

Mog

0.14

ftar

0.14

ÃŃses

0.14

tti

0.14

ibri

0.14

vÃ©d

0.14

Activations Density 0.098%

elements related to assignments and artistic projects

No Comments

No Known Activations