INDEX

Explanations

phrases indicating achievements and emotional responses in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Meg

-0.15

ero

-0.15

feed

-0.15

ä¸

-0.15

trap

-0.15

íĻľ

-0.14

 Cotton

-0.14

tl

-0.14

Progress

-0.14

 voyeur

-0.14

POSITIVE LOGITS

bst

0.16

ç·ł

0.16

anja

0.16

valuator

0.15

rane

0.15

ecta

0.15

 Modular

0.14

ansi

0.14

DED

0.14

oggle

0.14

Activations Density 0.184%

phrases indicating achievements and emotional responses in competitive contexts

No Comments

No Known Activations