INDEX

Explanations

instances of the word "experience" in various forms, focusing on feelings, events, and situations that people go through

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

dea

-0.16

portun

-0.15

ehler

-0.15

rlen

-0.15

 cerco

-0.15

erval

-0.14

ennie

-0.14

ix

-0.13

AKER

-0.13

Sno

-0.13

POSITIVE LOGITS

.StackTrace

0.17

onds

0.15

/console

0.14

CDATA

0.14

Åº

0.14

_detach

0.14

Ø¶Ø©

0.14

shan

0.14

ollen

0.14

ror

0.13

Activations Density 0.022%

instances of the word "experience" in various forms, focusing on feelings, events, and situations that people go through

No Comments

No Known Activations