INDEX

Explanations

occurrences of the word "In" or variations related to location or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

æĭ©

-0.19

achat

-0.15

å¿į

-0.14

ailure

-0.14

Ã¹ng

-0.14

ollow

-0.13

redi

-0.13

ç½Ĺæĸ¯

-0.13

Ð²Ð¾Ð»

-0.13

",__

-0.13

POSITIVE LOGITS

 journal

0.19

raÅ¾

0.16

yt

0.15

ÑĥÐ½Ð´

0.15

 Aber

0.15

Journal

0.14

yx

0.14

rix

0.14

 Journal

0.14

tid

0.14

Activations Density 0.002%

occurrences of the word "In" or variations related to location or context

No Comments

No Known Activations