INDEX

Explanations

references to specific individuals or characters, particularly those with the name "Ko" followed by a numeric identifier

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

rous

-0.16

ILLA

-0.16

-0.15

 Leap

-0.14

ilm

-0.14

Ø±

-0.14

trs

-0.14

abay

-0.14

lite

-0.13

 Commonwealth

-0.13

POSITIVE LOGITS

jes

0.19

agr

0.17

nev

0.16

ibel

0.15

abin

0.14

hlen

0.14

endor

0.14

ÑģÑı

0.14

rays

0.14

oser

0.14

Activations Density 0.006%

references to specific individuals or characters, particularly those with the name "Ko" followed by a numeric identifier

No Comments

No Known Activations