INDEX

Explanations

instances of emotional reactions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

aney

-0.17

ysz

-0.15

aman

-0.14

onse

-0.14

 addCriterion

-0.14

Gra

-0.14

 overriding

-0.14

MapView

-0.14

 craft

-0.14

blas

-0.14

POSITIVE LOGITS

.wp

0.19

ECH

0.15

ahl

0.14

osp

0.14

undry

0.14

ech

0.13

æĤ

0.13

aten

0.13

¬

0.13

mere

0.13

Activations Density 0.001%

instances of emotional reactions or sentiments

No Comments

No Known Activations