INDEX

Explanations

negative or uncertain sentiments and qualifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

YSTEM

-0.16

Ð¾Ð¿Ð°Ñģ

-0.15

teÅŁ

-0.14

-0.13

ertia

-0.13

vem

-0.13

ZeroWidthSpace

-0.13

ÑıÑĤÐ½Ð¾

-0.13

-shopping

-0.13

ewire

-0.13

POSITIVE LOGITS

ion

0.14

rious

0.14

 recently

0.14

awai

0.14

enco

0.13

elden

0.13

ikon

0.13

iguous

0.13

 unique

0.13

åĲ

0.12

Activations Density 0.343%

negative or uncertain sentiments and qualifiers

No Comments

No Known Activations