INDEX

Explanations

references to systematic approaches or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ager

-0.16

 Anim

-0.15

omap

-0.14

EventArgs

-0.14

 trai

-0.14

abil

-0.14

stitute

-0.14

ugi

-0.14

wp

-0.13

uo

-0.13

POSITIVE LOGITS

 Sachs

0.15

MOTE

0.14

.scalablytyped

0.14

ching

0.14

irling

0.14

_HAL

0.14

kÃ³w

0.14

elli

0.13

Activations Density 0.010%

references to systematic approaches or evaluations

No Comments

No Known Activations

references to systematic approaches or evaluations

No Comments

No Known Activations