INDEX

Explanations

concepts related to influence and power dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

vek

-0.16

-of

-0.16

ken

-0.15

eln

-0.15

uegos

-0.15

ven

-0.14

onth

-0.14

-than

-0.14

 ander

-0.14

posium

-0.14

POSITIVE LOGITS

icky

0.18

¯

0.15

 Bentley

0.14

ibold

0.14

Tro

0.14

RunWith

0.13

 ÑĢÐ¾Ñģ

0.13

itm

0.13

inline

0.13

 èģ

0.13

Activations Density 0.548%

concepts related to influence and power dynamics

No Comments

No Known Activations