INDEX

Explanations

conditional statements and logical constructs in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

SURE

-0.15

Ð¾ÑĢÐ¾Ð½Ð¸

-0.15

celik

-0.15

avin

-0.14

avy

-0.14

ibri

-0.14

ibur

-0.14

iÐ²

-0.14

tml

-0.14

(ml

-0.13

POSITIVE LOGITS

If

0.18

If

0.17

if

0.16

 Benson

0.15

Trace

0.15

ÑĢÑĥÐº

0.15

pies

0.14

 Trace

0.14

ETS

0.14

Activations Density 0.182%

conditional statements and logical constructs in the text

No Comments

No Known Activations