INDEX

Explanations

references to emotional perceptions and experiences in personal narratives

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

IMS

-0.15

iston

-0.15

Wik

-0.15

 verb

-0.14

fet

-0.14

æ¶Ī

-0.14

iffe

-0.14

.ts

-0.14

lish

-0.14

POSITIVE LOGITS

chy

0.18

iner

0.17

adir

0.17

arcer

0.16

0.15

 CallingConvention

0.14

ycz

0.14

erva

0.14

ariat

0.14

Activations Density 0.121%

references to emotional perceptions and experiences in personal narratives

No Comments

No Known Activations