INDEX

Explanations

assertions and discussions surrounding truth, facts, and beliefs related to specific issues and controversies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Æ°á»Ŀng

-0.15

tpl

-0.14

Î±Î½Î´

-0.14

nio

-0.13

Î¯Îº

-0.13

åł´

-0.13

å¿Ĺ

-0.13

_NV

-0.13

tel

-0.13

Overrides

-0.13

POSITIVE LOGITS

 facts

0.87

 fact

0.79

 Facts

0.72

facts

0.71

 Fact

0.68

 FACT

0.68

fact

0.66

Fact

0.65

_fact

0.59

FACT

0.59

Activations Density 0.218%

assertions and discussions surrounding truth, facts, and beliefs related to specific issues and controversies

No Comments

No Known Activations