INDEX

Explanations

occurrences of specific names or titles, particularly those beginning with "Gi."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ahoo

-0.16

ofire

-0.16

ington

-0.15

erman

-0.15

argo

-0.15

Ñĥ

-0.15

ansom

-0.14

al

-0.14

agen

-0.14

ersed

-0.14

POSITIVE LOGITS

'gc

0.16

ippi

0.15

Å¾el

0.15

ê²©

0.15

_RM

0.15

isay

0.14

CRY

0.14

curacy

0.14

à¸Ļà¸ª

0.14

 sublicense

0.14

Activations Density 0.014%

occurrences of specific names or titles, particularly those beginning with "Gi."

No Comments

No Known Activations