INDEX

Explanations

version numbers or decimals in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

oogle

-0.17

bourg

-0.17

oran

-0.16

TRACE

-0.16

ogenerated

-0.15

oucher

-0.15

tdown

-0.15

ØªÙĪÙĨ

-0.15

.Formatter

-0.14

nez

-0.14

POSITIVE LOGITS

Sap

0.16

Lik

0.16

 Ð·Ð°ÑģÑĤ

0.15

dfs

0.14

ifact

0.14

 dise

0.14

unic

0.14

porte

0.14

íĥķ

0.14

udent

0.14

Activations Density 0.033%

version numbers or decimals in a technical context

No Comments

No Known Activations