INDEX

Explanations

the word "Wh" and its variations, indicating a focus on questions or inquiry

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

abled

-0.16

ounge

-0.15

ez

-0.15

usc

-0.15

ificates

-0.15

FLICT

-0.15

ival

-0.15

abel

-0.15

ideon

-0.14

unction

-0.14

POSITIVE LOGITS

ew

0.18

Wh

0.18

ATAB

0.18

itting

0.17

ys

0.17

oles

0.16

oso

0.16

istle

0.16

olesale

0.16

SUP

0.15

Activations Density 0.015%

the word "Wh" and its variations, indicating a focus on questions or inquiry

No Comments

No Known Activations