INDEX

Explanations

names of individuals associated with various contexts or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

éĺ

-0.15

yh

-0.15

oda

-0.14

Tap

-0.14

asis

-0.13

ãģ£

-0.13

.dw

-0.13

ette

-0.13

.yy

-0.13

POSITIVE LOGITS

encodeURIComponent

0.15

goog

0.15

ampo

0.14

_hop

0.14

 prest

0.14

ØµØ¯

0.13

Enc

0.13

gings

0.13

;break

0.13

jsx

0.13

Activations Density 0.417%

names of individuals associated with various contexts or events

No Comments

No Known Activations