INDEX

Explanations

references to time and changes in circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

amiliar

-0.16

 familiar

-0.15

 Hamm

-0.15

ction

-0.14

 compound

-0.14

isposable

-0.14

zen

-0.14

reator

-0.14

áº¯m

-0.13

orsche

-0.13

POSITIVE LOGITS

anas

0.16

ronic

0.15

shm

0.15

0.14

ongo

0.14

fx

0.14

ullo

0.14

ether

0.14

anco

0.14

PMC

0.14

Activations Density 0.099%

references to time and changes in circumstances

No Comments

No Known Activations