INDEX

Explanations

commands or suggestions related to actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

acin

-0.16

sian

-0.15

ains

-0.15

urrent

-0.14

QRST

-0.14

.rf

-0.14

Ã£n

-0.14

/Internal

-0.14

ä¿

-0.14

flat

-0.14

POSITIVE LOGITS

Ùī

0.15

 correspond

0.15

ost

0.15

amam

0.15

ingers

0.15

itor

0.14

mon

0.14

º

0.14

yo

0.14

Ost

0.14

Activations Density 0.017%

commands or suggestions related to actions or events

No Comments

No Known Activations