INDEX

Explanations

positive descriptors and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

adolu

-0.19

ityEngine

-0.17

entialAction

-0.17

ì¸ł

-0.15

@qq

-0.15

ãĤį

-0.14

Ħĸ

-0.14

weetalert

-0.14

fillType

-0.13

pNet

-0.13

POSITIVE LOGITS

arse

0.17

icy

0.14

asc

0.14

iform

0.14

yp

0.14

0.13

isky

0.13

asics

0.13

odel

0.13

Activations Density 0.016%

positive descriptors and evaluations

No Comments

No Known Activations