INDEX

Explanations

occurrences and references to the concept of "value" in various contexts

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

umber

-0.17

lace

-0.17

zeit

-0.16

ly

-0.16

rego

-0.15

imal

-0.15

lio

-0.15

tega

-0.15

nÃŃ

-0.15

like

-0.15

POSITIVE LOGITS

-added

0.33

0.25

holder

0.21

åŁŁ

0.20

 propositions

0.20

 proposition

0.20

less

0.19

-nil

0.19

å¾Ĺ

0.18

lessness

0.18

Activations Density 0.108%

occurrences and references to the concept of "value" in various contexts

No Comments

No Known Activations