INDEX

Explanations

occurrences of the word "here" 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ses

-0.20

ities

-0.18

âĦĸ

-0.18

ulu

-0.15

geb

-0.15

egas

-0.15

poc

-0.15

elin

-0.15

ville

-0.14

ss

-0.14

POSITIVE LOGITS

after

0.24

ìłĢ

0.21

ault

0.18

ina

0.17

orthand

0.16

jÅ¡ÃŃ

0.15

Å¡ak

0.15

usalem

0.15

ulla

0.14

Activations Density 0.087%

occurrences of the word "here" in various contexts

No Comments

No Known Activations