INDEX

Explanations

statements related to assumptions and considerations in theoretical discussions

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

aget

-0.16

Ð°Ð»Ð¾Ð²

-0.15

½æķ°

-0.14

Ð½Ð¸ÐºÐ¾Ð²

-0.14

appers

-0.14

metro

-0.14

aton

-0.14

fcn

-0.14

stead

-0.13

aston

-0.13

POSITIVE LOGITS

ingham

0.16

0.15

 Schneider

0.15

 Abrams

0.14

0.13

Activations Density 0.076%

statements related to assumptions and considerations in theoretical discussions

No Comments

No Known Activations