INDEX

Explanations

references to technology and devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Pussy

-0.16

 Aires

-0.14

Ø§ÙĦØµ

-0.14

eam

-0.13

 caller

-0.13

dp

-0.13

 Ð´Ð²Ð¾

-0.13

eland

-0.13

elop

-0.13

 Stad

-0.13

POSITIVE LOGITS

edImage

0.16

 pupper

0.15

iano

0.15

'ye

0.14

ifact

0.14

PRINTF

0.14

imenti

0.14

nee

0.14

âĸį

0.13

ems

0.13

Activations Density 0.082%

references to technology and devices

No Comments

No Known Activations