INDEX

Explanations

frequent occurrences of specific articles and conjunctions used in context

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

âĢ¦

-0.15

Ø¹Ø¨

-0.14

âĢ

-0.14

 tÃŃ

-0.13

 during

-0.13

à¸²à¸ģ

-0.12

 brave

-0.12

 stol

-0.12

POSITIVE LOGITS

(éĩĳ

0.16

erif

0.15

vailability

0.15

 ÑĦÑĥÐ½Ð´Ð°

0.14

CallCheck

0.14

ehir

0.14

ÅĻÃŃm

0.14

Slinky

0.14

STALL

0.14

emachine

0.14

Activations Density 0.018%

frequent occurrences of specific articles and conjunctions used in context

No Comments

No Known Activations