INDEX

Explanations

phrases that express potential or possibilities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eter

-0.16

-ÑĤÐ¾

-0.15

islav

-0.15

ujet

-0.15

nek

-0.15

swick

-0.15

imming

-0.14

late

-0.14

ãģ¿

-0.14

Ã³z

-0.14

POSITIVE LOGITS

mente

0.17

-bodied

0.15

keiten

0.15

ioned

0.15

oÅĻ

0.15

ayout

0.15

FULL

0.14

ippets

0.14

Activations Density 0.053%

phrases that express potential or possibilities

No Comments

No Known Activations