INDEX

Explanations

patterns related to coding and programming concepts

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

ylko

-0.16

ITTE

-0.15

 scor

-0.14

OffsetTable

-0.14

çº

-0.14

itung

-0.14

meyi

-0.14

ubar

-0.14

lette

-0.14

otte

-0.13

POSITIVE LOGITS

acha

0.16

0.15

atas

0.14

ochen

0.14

arcy

0.14

echan

0.13

alth

0.13

 Ingram

0.13

erta

0.13

cala

0.13

Activations Density 0.115%

patterns related to coding and programming concepts

No Comments

No Known Activations