INDEX

Explanations

phrases that express caution or recommendations regarding actions and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

berger

-0.15

Ã¨m

-0.15

elle

-0.15

lez

-0.15

 Vapor

-0.14

chrift

-0.14

illa

-0.14

 ìĿ´ëıĻíķ©ëĭĪëĭ¤

-0.14

urger

-0.14

resco

-0.14

POSITIVE LOGITS

ola

0.15

kk

0.15

EDIUM

0.14

umi

0.14

 Intr

0.14

Ã¥

0.14

è¼¸

0.14

thy

0.14

cci

0.14

 acquaintance

0.13

Activations Density 0.280%

phrases that express caution or recommendations regarding actions and their consequences

No Comments

No Known Activations