INDEX

Explanations

phrases indicating clarity or perception regarding various situations or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elman

-0.18

nown

-0.16

vik

-0.15

beck

-0.15

hape

-0.15

 concrete

-0.15

tery

-0.14

Ð¾Ð¼ÐµÐ½

-0.14

pty

-0.14

quette

-0.14

POSITIVE LOGITS

0.16

èĮĤ

0.15

unction

0.14

atten

0.14

Æ¡n

0.14

iano

0.14

éĶĭ

0.14

cuts

0.13

enus

0.13

mad

0.13

Activations Density 0.055%

phrases indicating clarity or perception regarding various situations or conditions

No Comments

No Known Activations