INDEX

Explanations

adaptive words and phrases related to representations of places or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

avin

-0.15

clusive

-0.15

isz

-0.15

oul

-0.15

 alike

-0.14

 cupid

-0.14

à¥Ĥà¤ģ

-0.14

for

-0.14

fan

-0.13

alus

-0.13

POSITIVE LOGITS

endl

0.16

 erken

0.15

ijken

0.14

CEEDED

0.14

_framework

0.14

_connector

0.14

ÛĮÙĩ

0.14

empo

0.14

ityEngine

0.14

kit

0.14

Activations Density 0.064%

adaptive words and phrases related to representations of places or locations

No Comments

No Known Activations