INDEX

Explanations

connections between phrases or concepts and their interpretations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

stro

-0.15

.FC

-0.15

iam

-0.15

 Airways

-0.14

erring

-0.14

nech

-0.14

yat

-0.14

bing

-0.14

lems

-0.14

luv

-0.14

POSITIVE LOGITS

olie

0.15

InBackground

0.14

aval

0.14

ereo

0.13

iny

0.13

iente

0.13

ÐµÑĢÐ³

0.13

BindView

0.13

nes

0.13

Activations Density 0.130%

connections between phrases or concepts and their interpretations

No Comments

No Known Activations