INDEX

Explanations

references to geopolitical events and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

visor

-0.16

leftrightarrow

-0.15

 drawn

-0.14

 IDisposable

-0.14

LING

-0.14

CADE

-0.13

 insign

-0.13

abin

-0.13

 dent

-0.13

CAB

-0.13

POSITIVE LOGITS

unce

0.17

ç¥¥

0.16

rrha

0.16

fst

0.15

ather

0.15

ibase

0.15

ewe

0.15

 Farr

0.14

rale

0.14

lesc

0.14

Activations Density 0.164%

references to geopolitical events and their implications

No Comments

No Known Activations