INDEX

Explanations

references to academic departments or institutions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

orp

-0.16

iaux

-0.15

uku

-0.15

 Robbins

-0.14

tre

-0.14

za

-0.14

igne

-0.14

otti

-0.14

 Dickens

-0.14

ÑĢÐ¾Ð²Ð¾Ð´

-0.14

POSITIVE LOGITS

piel

0.18

dom

0.15

å¤«

0.15

askan

0.15

bler

0.14

rices

0.14

ahren

0.14

REAK

0.13

 Next

0.13

iete

0.13

Activations Density 0.002%

references to academic departments or institutions

No Known Activations