INDEX

Explanations

the use of the word “pod” in contexts related to groups or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ikit

-0.16

vely

-0.15

Ð´Ñĭ

-0.15

steller

-0.14

å±ħ

-0.14

stakes

-0.14

peed

-0.14

ushima

-0.14

pearance

-0.13

chten

-0.13

POSITIVE LOGITS

 patron

0.19

 pseud

0.19

lie

0.19

seud

0.18

arken

0.18

 guise

0.17

neath

0.16

 influence

0.16

 ausp

0.16

Activations Density 0.007%

the use of the word “pod” in contexts related to groups or categories

No Comments

No Known Activations