INDEX

Explanations

expressions of contrasting ideas or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ost

-0.15

lesi

-0.14

 Wass

-0.13

InterfaceOrientation

-0.13

å¹³

-0.13

Ł

-0.13

 verte

-0.13

ÑĢÐ¾Ñī

-0.13

æīĭãĤĴ

-0.13

Mut

-0.13

POSITIVE LOGITS

ters

0.18

è¿ĺæĺ¯

0.17

 Still

0.17

 still

0.17

Still

0.16

 nevertheless

0.16

 ìĹ¬

0.15

izzo

0.15

 Nevertheless

0.14

still

0.14

Activations Density 0.184%

expressions of contrasting ideas or conditions

No Comments

No Known Activations