INDEX

Explanations

references to educational experiences and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

isas

-0.15

cts

-0.15

ct

-0.14

uga

-0.14

unya

-0.14

unger

-0.14

 Sure

-0.14

umber

-0.14

usi

-0.14

POSITIVE LOGITS

ãĥĥãĥĦ

0.16

 Bakan

0.15

 Ø¹Ø²

0.15

ÙĮ

0.15

TERN

0.15

Hud

0.14

_EP

0.14

èŃ

0.14

 Ferd

0.14

 å¤§éĺª

0.14

Activations Density 0.372%

references to educational experiences and qualifications

No Comments

No Known Activations