INDEX

Explanations

words related to choices and decisions

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

ugin

-0.17

zer

-0.15

exus

-0.15

newsletter

-0.14

oun

-0.14

ï¼£

-0.14

visor

-0.14

Newsletter

-0.13

Ð¾ÑĤÐ¾Ð²

-0.13

quist

-0.13

POSITIVE LOGITS

@js

0.15

0.14

.ic

0.14

rah

0.14

ocol

0.14

 Damen

0.14

 Perr

0.14

art

0.14

 supra

0.13

antan

0.13

Activations Density 0.610%

words related to choices and decisions

No Comments

No Known Activations