INDEX

Explanations

references to quantitative data or statistics

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

emen

-0.17

emento

-0.16

Ø§Ø±Ø´

-0.15

ums

-0.14

wor

-0.14

setType

-0.14

iae

-0.13

-Origin

-0.13

ru

-0.13

CAPE

-0.13

POSITIVE LOGITS

 Harden

0.16

ÙĪÚ¯Ø±

0.15

lund

0.15

ÏĢÎ¹Ïĥ

0.14

anden

0.14

riad

0.14

ozor

0.14

Ð¾ÑĤÐ°

0.14

Bearer

0.14

odiac

0.14

Activations Density 0.221%

references to quantitative data or statistics

No Comments

No Known Activations