INDEX

Explanations

references to power, particularly in the context of authority, energy, or influence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

orgen

-0.17

enerator

-0.17

berger

-0.15

Torrent

-0.14

fabs

-0.14

hd

-0.13

ĽĪ

-0.13

íĹĮ

-0.13

 Hakk

-0.13

avou

-0.13

POSITIVE LOGITS

lier

0.17

agged

0.17

ORB

0.16

mtree

0.15

anted

0.15

eil

0.15

Ð»ÑĥÐ³

0.15

erd

0.14

lek

0.14

Activations Density 0.027%

references to power, particularly in the context of authority, energy, or influence

No Comments

No Known Activations