INDEX

Explanations

elements discussing evaluation and judgment in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

elda

-0.16

ERSHEY

-0.15

eld

-0.15

raj

-0.14

clud

-0.14

urdu

-0.14

ectl

-0.14

eldorf

-0.14

 Geile

-0.14

halb

-0.14

POSITIVE LOGITS

 experience

0.16

EMU

0.15

emode

0.15

à¹Ģà¸ģà¸¥

0.14

 recent

0.14

 vestib

0.14

qd

0.14

kowski

0.13

ÑĥÐ»Ñı

0.13

experience

0.13

Activations Density 0.117%

elements discussing evaluation and judgment in various contexts

No Comments

No Known Activations