INDEX

Explanations

instances of the word "Rou" and its variations, indicating a focus on mentions of a specific location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ñĥ

-0.17

rade

-0.16

idge

-0.15

RI

-0.15

nels

-0.15

rr

-0.14

rium

-0.14

Ãłn

-0.14

ases

-0.14

oods

-0.14

POSITIVE LOGITS

illard

0.21

illet

0.21

ille

0.19

thern

0.18

theast

0.18

illon

0.17

cou

0.17

lt

0.17

ette

0.17

Activations Density 0.030%

instances of the word "Rou" and its variations, indicating a focus on mentions of a specific location

No Comments

No Known Activations