INDEX

Explanations

terms related to influence or the act of influencing

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

binations

-0.16

rael

-0.14

mium

-0.14

licate

-0.14

ÎŃÏģÎ±

-0.14

ìŀĶ

-0.14

ivant

-0.14

onta

-0.13

isque

-0.13

áº§m

-0.13

POSITIVE LOGITS

 Blaze

0.15

ESS

0.14

apore

0.14

SSION

0.14

odi

0.13

STD

0.13

 Ashe

0.13

 Bentley

0.13

ably

0.13

Activations Density 0.013%

terms related to influence or the act of influencing

No Comments

No Known Activations