INDEX

Explanations

references to the term "angular" 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aines

-0.17

ess

-0.15

ãĤ·ãĥ¼

-0.14

istrovstvÃŃ

-0.14

PLEX

-0.14

ensus

-0.14

ignum

-0.13

Î»Î®

-0.13

Ð»Ð°Ð³Ð°

-0.13

inf

-0.13

POSITIVE LOGITS

umb

0.15

sten

0.15

 GrÃ¼

0.15

ÄįÃŃ

0.15

rear

0.15

reas

0.15

åŃ

0.14

åº¦

0.14

 smash

0.14

Activations Density 0.006%

references to the term "angular" in various contexts

No Comments

No Known Activations