INDEX

Explanations

numeric and ordinal representations related to dates, years, and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

$MESS

-0.17

jourd

-0.15

laps

-0.14

Touches

-0.13

parable

-0.13

eÄį

-0.13

paces

-0.13

ipc

-0.13

 tá»¥

-0.12

 Strikes

-0.12

POSITIVE LOGITS

eri

0.15

ÏĥÏĦÎµ

0.15

urm

0.15

kla

0.14

atos

0.14

dez

0.13

inson

0.13

ernes

0.13

ndef

0.13

alue

0.13

Activations Density 0.310%

numeric and ordinal representations related to dates, years, and events

No Comments

No Known Activations