INDEX

Explanations

numeric data and year references in events or timelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

byn

-0.18

yr

-0.15

çĩ

-0.15

-0.14

otre

-0.14

rink

-0.14

vida

-0.14

ota

-0.14

Vir

-0.14

-0.13

POSITIVE LOGITS

ÙĦØ§Ùģ

0.16

agher

0.16

ypse

0.16

PointerType

0.15

oin

0.14

cba

0.14

Ø§Øº

0.14

MSG

0.13

hausen

0.13

UILD

0.13

Activations Density 0.024%

numeric data and year references in events or timelines

No Comments

No Known Activations