INDEX

Explanations

statements expressing uncertainty, likelihood, or the potential for different interpretations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

oris

-0.16

Ãºp

-0.14

 Truly

-0.14

.AspNet

-0.14

ACHI

-0.14

abo

-0.14

ora

-0.14

 truly

-0.14

acro

-0.14

orca

-0.14

POSITIVE LOGITS

 certainly

0.17

maybe

0.16

 maybe

0.16

arger

0.15

 probably

0.15

mos

0.14

ither

0.14

icher

0.14

ewire

0.14

occ

0.14

Activations Density 0.009%

statements expressing uncertainty, likelihood, or the potential for different interpretations

No Comments

No Known Activations