INDEX

Explanations

references to measurement or quantification in research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Äįer

-0.15

 Mellon

-0.15

eken

-0.15

 vars

-0.14

ÃĥO

-0.14

 arch

-0.13

ingu

-0.13

_LANG

-0.13

usu

-0.13

CCA

-0.13

POSITIVE LOGITS

ãĥªãĥ¼ãĤº

0.16

arella

0.16

éĺħè¯»æ¬¡æķ°

0.15

ÑĻ

0.15

ufs

0.14

Ð¾Ð²Ð¶

0.14

abei

0.14

 ê·ľ

0.13

 vrou

0.13

Activations Density 0.097%

references to measurement or quantification in research contexts

No Comments

No Known Activations