INDEX

Explanations

occurrences of the letter "E" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Stafford

-0.15

 McLaren

-0.15

ãĤ©

-0.14

LIC

-0.14

 misc

-0.14

med

-0.14

IFIC

-0.13

ICT

-0.13

Ãª

-0.13

orth

-0.13

POSITIVE LOGITS

 commerce

0.17

ucken

0.16

cade

0.15

ëĮĢíķľ

0.15

 dilig

0.15

.ON

0.14

.Servlet

0.14

.attrs

0.14

commerce

0.14

ibbon

0.14

Activations Density 0.039%

occurrences of the letter "E" in various contexts

No Comments

No Known Activations