INDEX

Explanations

references to information and its various forms

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

 Lump

-0.17

uko

-0.14

elp

-0.14

ANA

-0.14

per

-0.14

inas

-0.13

-mounted

-0.13

 nhiÃªn

-0.13

infeld

-0.13

our

-0.13

POSITIVE LOGITS

 nackte

0.16

 prÅ¯bÄĽhu

0.15

imbus

0.14

eum

0.14

ellen

0.14

SSION

0.14

_VC

0.14

ODEV

0.14

nist

0.14

ODE

0.14

Activations Density 0.065%

references to information and its various forms

No Comments

No Known Activations