INDEX

Explanations

words indicating value, transactions, and time-related actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

DMI

-0.17

ĽĦ

-0.16

à¤Łà¤ķ

-0.16

-0.14

ubb

-0.14

MITTED

-0.14

avier

-0.14

 çľģ

-0.14

ç¦

-0.14

ÑģÑĤÑĢÑĥ

-0.13

POSITIVE LOGITS

.community

0.16

 ensemble

0.15

ota

0.15

APTER

0.14

 Ensemble

0.14

ottes

0.14

_stdio

0.14

.TestTools

0.13

oto

0.13

PGA

0.13

Activations Density 0.007%

words indicating value, transactions, and time-related actions

No Comments

No Known Activations