INDEX

Explanations

prepositions and phrases indicating location and time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

shr

-0.15

antan

-0.14

uras

-0.13

-mar

-0.13

argo

-0.13

 Measure

-0.13

UDA

-0.13

warm

-0.13

ho

-0.13

ONTAL

-0.13

POSITIVE LOGITS

herits

0.17

áº¡n

0.16

onis

0.15

Fon

0.15

ipse

0.15

tractor

0.14

ÑıÐ½

0.14

anes

0.14

inges

0.14

mobx

0.14

Activations Density 0.662%

prepositions and phrases indicating location and time

No Comments

No Known Activations