INDEX

Explanations

negative sentiments and expressions of disbelief

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

literal

-0.17

DOMNode

-0.15

_VC

-0.15

 soudu

-0.15

ë²Į

-0.14

 literal

-0.14

vero

-0.14

éĢ¸

-0.14

gere

-0.14

aÃ§

-0.14

POSITIVE LOGITS

cip

0.18

0.16

loff

0.16

adol

0.16

PEC

0.16

 ones

0.15

 Hairst

0.15

ifestyles

0.15

Activations Density 0.060%

negative sentiments and expressions of disbelief

No Comments

No Known Activations