INDEX

Explanations

instances of the word "posted" and its variations, indicating a focus on sharing or announcing information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.16

quent

-0.15

QUARE

-0.15

 Robbins

-0.14

ably

-0.14

ournal

-0.14

OrCreate

-0.14

 personally

-0.13

NB

-0.13

POSITIVE LOGITS

pone

0.21

phyl

0.20

 onto

0.20

natal

0.19

/post

0.18

ulate

0.18

 bail

0.17

iffs

0.16

 lÃªn

0.16

onto

0.16

Activations Density 0.032%

instances of the word "posted" and its variations, indicating a focus on sharing or announcing information

No Comments

No Known Activations