INDEX

Explanations

elements related to organization or structure within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Morgan

-0.21

 Millet

-0.21

mile

-0.21

 Mand

-0.19

 Meyer

-0.19

 Mile

-0.19

alam

-0.19

 Milton

-0.18

 Marty

-0.18

 Messenger

-0.17

POSITIVE LOGITS

 match

0.79

-match

0.71

match

0.69

 matches

0.69

 Match

0.62

.match

0.61

_match

0.61

 MATCH

0.59

Match

0.58

 matched

0.58

Activations Density 0.257%

elements related to organization or structure within a context

No Comments

No Known Activations

elements related to organization or structure within a context

No Comments

No Known Activations