INDEX

Explanations

discussions about decision-making processes in the context of changing circumstances and historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 lenght

-0.18

linger

-0.14

 Brace

-0.14

ç¨

-0.14

åĤ¬

-0.14

abi

-0.14

tail

-0.14

atom

-0.13

ÐµÐ¹

-0.13

neh

-0.13

POSITIVE LOGITS

isbury

0.16

robat

0.15

WT

0.14

oler

0.14

ificate

0.14

 Strong

0.14

PPER

0.14

ÏģÏİÎ½

0.14

Cal

0.13

Activations Density 0.019%

discussions about decision-making processes in the context of changing circumstances and historical events

No Comments

No Known Activations