INDEX

Explanations

occurrences of the article "a" and its related forms

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

.createFrom

-0.16

vu

-0.16

etsk

-0.15

 Hust

-0.15

argent

-0.15

-0.14

sek

-0.13

 thoáº¡i

-0.13

 Terms

-0.13

 Punch

-0.13

POSITIVE LOGITS

moth

0.15

ãĥ³ãĥ

0.15

thro

0.14

å¤®

0.14

ular

0.14

oyal

0.14

modele

0.14

asis

0.13

linger

0.13

Bubble

0.13

Activations Density 0.025%

occurrences of the article "a" and its related forms

No Comments

No Known Activations