INDEX

Explanations

occurrences of summary statements and conclusions 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 @ 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

dana

-0.17

inta

-0.16

 Gund

-0.15

è°

-0.14

iven

-0.14

ç¨¿

-0.14

ÏĤ

-0.14

anje

-0.13

Hel

-0.13

ettel

-0.13

POSITIVE LOGITS

osaur

0.17

onis

0.15

estation

0.15

oni

0.15

odyn

0.15

entence

0.15

chied

0.14

ucer

0.14

odesk

0.14

_OVERRIDE

0.14

Activations Density 0.232%

occurrences of summary statements and conclusions in the text

No Comments

No Known Activations