INDEX

Explanations

code snippets related to HTML and CSS manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÑĥÑĪ

-0.15

isoft

-0.14

baum

-0.14

aldi

-0.14

bilt

-0.14

 Orient

-0.14

//=

-0.14

irie

-0.14

çı

-0.14

POSITIVE LOGITS

div

0.19

ul

0.18

ul

0.17

span

0.17

UL

0.16

li

0.16

otre

0.16

ancia

0.16

 span

0.16

lopedia

0.15

Activations Density 0.040%

code snippets related to HTML and CSS manipulation

No Comments

No Known Activations