INDEX

Explanations

proper nouns, specifically names of places and people

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

_flutter

-0.17

agus

-0.15

onis

-0.15

ung

-0.14

(SIG

-0.14

veh

-0.14

sis

-0.14

eria

-0.14

CR

-0.14

ccount

-0.13

POSITIVE LOGITS

ensis

0.23

-based

0.17

tez

0.15

haven

0.15

ienne

0.14

licated

0.14

olt

0.14

 Wander

0.13

 Chronicle

0.13

edik

0.13

Activations Density 0.541%

proper nouns, specifically names of places and people

No Comments

No Known Activations