INDEX

Explanations

expressions of satisfaction and acknowledgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Baby

-0.16

 Union

-0.16

Embed

-0.16

Explicit

-0.16

-0.15

inc

-0.15

 Lynn

-0.15

une

-0.15

wp

-0.15

POSITIVE LOGITS

chal

0.17

roc

0.16

emade

0.16

GetString

0.15

esser

0.15

ether

0.15

_ping

0.15

åľį

0.15

shint

0.15

_salt

0.15

Activations Density 0.019%

expressions of satisfaction and acknowledgment

No Comments

No Known Activations