INDEX

Explanations

references to time-related parameters and variables

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ovky

-0.17

ENAME

-0.16

wiki

-0.15

ulk

-0.15

ActionTypes

-0.14

ula

-0.13

entina

-0.13

entes

-0.13

ivial

-0.13

ë²Ī

-0.13

POSITIVE LOGITS

.dds

0.17

è²´

0.16

arkin

0.16

allet

0.15

 Ø§ÙĦÙĤØ¯

0.14

othy

0.14

uste

0.14

uong

0.14

SP

0.14

Activations Density 0.049%

references to time-related parameters and variables

No Comments

No Known Activations