INDEX

Explanations

statements reflecting personal experiences and emotions

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

ollen

-0.19

ektiv

-0.17

irit

-0.16

semb

-0.15

utow

-0.15

onnement

-0.14

vice

-0.14

gado

-0.14

ccione

-0.14

typed

-0.14

POSITIVE LOGITS

ÎµÏħ

0.15

ze

0.14

hammer

0.14

when

0.14

 rejo

0.13

aman

0.13

rys

0.13

fel

0.13

ze

0.13

aj

0.13

Activations Density 0.367%

statements reflecting personal experiences and emotions

No Comments

No Known Activations