INDEX

Explanations

statements that express observations or insights about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

avic

-0.15

bla

-0.14

 Others

-0.14

elf

-0.14

ÑĨÐ¾

-0.14

Ú©ÙĨØ§ÙĨ

-0.13

 perch

-0.13

Ð¶

-0.13

ilent

-0.13

ifa

-0.13

POSITIVE LOGITS

 constant

0.17

acker

0.17

ìķħ

0.16

tlement

0.15

 certainty

0.15

itious

0.15

nota

0.15

strike

0.15

vester

0.15

 consistent

0.15

Activations Density 0.075%

statements that express observations or insights about various subjects

No Comments

No Known Activations