INDEX

Explanations

phrases or actions related to settling or establishing a position

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ansson

-0.20

 Schultz

-0.18

enberg

-0.17

ensch

-0.16

eneg

-0.15

OptionsMenu

-0.15

itors

-0.15

acular

-0.15

sa

-0.15

selectedIndex

-0.14

POSITIVE LOGITS

hetto

0.16

arr

0.16

ford

0.15

oya

0.15

readcr

0.15

obre

0.14

bred

0.14

thane

0.14

uplicates

0.14

Activations Density 0.168%

phrases or actions related to settling or establishing a position

No Comments

No Known Activations