INDEX

Explanations

occurrences of emotional responses and reflections on experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.15

cola

-0.14

ifiers

-0.14

eval

-0.14

 buoy

-0.14

ÑĸÐ½Ð¾

-0.14

pod

-0.13

 Ø§ÙĦØ¶

-0.13

uffers

-0.13

.gwt

-0.13

POSITIVE LOGITS

á»ĥn

0.18

 Crack

0.17

zap

0.16

á»

0.16

.toLocale

0.15

-account

0.15

/logging

0.14

unan

0.14

-minus

0.14

amet

0.14

Activations Density 0.212%

occurrences of emotional responses and reflections on experiences

No Comments

No Known Activations