INDEX

Explanations

references to political terms and office durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

fic

-0.19

-0.16

oon

-0.15

eden

-0.14

/fire

-0.14

oder

-0.14

OFFSET

-0.14

adors

-0.13

.Offset

-0.13

 McInt

-0.13

POSITIVE LOGITS

chio

0.16

ninger

0.15

_sampler

0.15

ureau

0.15

idir

0.14

æĩī

0.14

anh

0.14

Mate

0.14

.synthetic

0.13

 MatSnackBar

0.13

Activations Density 0.014%

references to political terms and office durations

No Comments

No Known Activations