INDEX

Explanations

phrases involving higher levels of specificity, often indicating a contrast or differentiation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

(éĩĳ

-0.15

ÅĻet

-0.15

ropa

-0.15

atural

-0.14

MMdd

-0.14

ç§

-0.14

ittle

-0.14

 SAME

-0.14

SSF

-0.13

rng

-0.13

POSITIVE LOGITS

ahren

0.14

ennie

0.14

avian

0.13

 Trot

0.13

Tro

0.13

ubu

0.13

.Unlock

0.13

 parental

0.13

(INFO

0.13

acen

0.13

Activations Density 0.177%

phrases involving higher levels of specificity, often indicating a contrast or differentiation

No Comments

No Known Activations