INDEX

Explanations

instances of the word "park" and its variations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÑĢÑĥÐ½

-0.16

/ay

-0.15

à¸Ńà¸ĩà¸Īà¸²à¸ģ

-0.15

aten

-0.15

encers

-0.15

-0.14

enta

-0.14

VERR

-0.14

pedo

-0.14

POSITIVE LOGITS

ãģĭãģĳ

0.17

Ð»Ð°Ð½Ð´

0.15

ipl

0.15

 inval

0.14

ì§Ŀ

0.14

acie

0.13

 distant

0.13

Courier

0.13

 stake

0.13

Activations Density 0.016%

instances of the word "park" and its variations in the text

No Comments

No Known Activations