INDEX

Explanations

references to external sources and citations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Washer

-0.16

 -*-č↵

-0.15

ignal

-0.14

irm

-0.14

_DEFINE

-0.14

 dispatcher

-0.14

argo

-0.14

 Washing

-0.14

-hide

-0.13

{})

-0.13

POSITIVE LOGITS

 Pett

0.18

iyel

0.16

uluk

0.15

hlas

0.14

 tribute

0.13

elight

0.13

imals

0.13

ilik

0.13

glomer

0.13

Activations Density 0.032%

references to external sources and citations in the text

No Comments

No Known Activations