INDEX

Explanations

key phrases and action-oriented terms related to sharing content or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÅĻe

-0.18

alles

-0.16

blick

-0.16

itch

-0.15

kÃ¶

-0.15

ura

-0.15

ichi

-0.14

ãģŁãģĹ

-0.13

eniz

-0.13

 ç±

-0.13

POSITIVE LOGITS

hte

0.17

mtree

0.15

 Lever

0.15

aucoup

0.14

_mirror

0.14

_SENSOR

0.14

Ð¾Ð»Ñĸ

0.14

ngle

0.14

ãĥ¼ãĥł

0.14

Activations Density 0.002%

key phrases and action-oriented terms related to sharing content or experiences

No Comments

No Known Activations