INDEX

Explanations

occurrences of the word "for" and other prepositions indicating purpose or reason

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

aks

-0.17

ezier

-0.15

-0.14

MOTE

-0.13

iram

-0.13

åĬ¨çĶŁæĪĲ

-0.13

okt

-0.13

ìĿ´ìķ¼

-0.12

antry

-0.12

POSITIVE LOGITS

zyst

0.17

ello

0.17

Ð¾Ð»Ð¾Ñģ

0.16

YPRE

0.14

/us

0.14

ippers

0.14

usercontent

0.14

osite

0.14

iba

0.14

ools

0.14

Activations Density 0.035%

occurrences of the word "for" and other prepositions indicating purpose or reason

No Comments

No Known Activations