INDEX

Explanations

references to problem-solving and adherence to procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.17

-0.16

Ø§ØŃØª

-0.16

phia

-0.15

ds

-0.15

aille

-0.15

-0.14

uro

-0.14

.setViewport

-0.14

POSITIVE LOGITS

hog

0.16

ighter

0.16

izzy

0.15

brero

0.15

LEC

0.15

odyn

0.15

czy

0.14

agi

0.14

Descriptor

0.14

agus

0.14

Activations Density 0.016%

references to problem-solving and adherence to procedures

No Comments

No Known Activations