INDEX

Explanations

specific numerical data and references to events and categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ubl

-0.16

cul

-0.16

hausen

-0.16

oya

-0.15

ãĤ¤ãĤ¯

-0.15

Å¡ti

-0.15

agini

-0.14

hari

-0.14

Tan

-0.14

 addCriterion

-0.14

POSITIVE LOGITS

åīĽ

0.15

metis

0.15

ollo

0.15

Ø¹Ø§Ùħ

0.14

loit

0.14

Frames

0.14

abbo

0.14

avax

0.14

ccione

0.13

Activations Density 0.030%

specific numerical data and references to events and categories

No Comments

No Known Activations