INDEX

Explanations

technical terms related to scientific studies and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ecome

-0.16

ķãĤĵ

-0.15

ramids

-0.14

lotte

-0.14

OOT

-0.14

ntl

-0.14

ambre

-0.14

à¸°à¹ģ

-0.13

 ëį¤íĶĦ

-0.13

laden

-0.13

POSITIVE LOGITS

¤

0.16

 ↵ ↵

0.14

âĢ¯

0.14

č

0.13

 ï»¿

0.13

.pdf

0.13

annes

0.12

ered

0.12

 âĢ¯

0.12

eres

0.12

Activations Density 0.010%

technical terms related to scientific studies and methodologies

No Comments

No Known Activations