INDEX

Explanations

verbs indicating movement or transition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

anne

-0.19

ones

-0.15

verty

-0.15

Ãº

-0.14

Dob

-0.14

rette

-0.14

htub

-0.14

aldo

-0.13

 McGu

-0.13

tres

-0.13

POSITIVE LOGITS

 into

0.19

into

0.18

 back

0.16

 onto

0.15

inton

0.15

NonQuery

0.15

akis

0.14

ipse

0.14

Ð¾Ð·Ñı

0.14

illis

0.14

Activations Density 0.079%

verbs indicating movement or transition

No Comments

No Known Activations