INDEX

Explanations

mentions of "first things" or significant initial actions in a narrative

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

llib

-0.16

rieve

-0.16

Ã¢u

-0.16

atto

-0.15

brew

-0.14

StackSize

-0.14

ent

-0.14

mÃŃ

-0.14

rowable

-0.14

quette

-0.14

POSITIVE LOGITS

mant

0.17

 thing

0.16

 Pods

0.16

è´

0.15

inch

0.15

ÑģÑĤÑĥÐ¿

0.15

ãĥ«ãĤ¯

0.15

ÑģÑĤÐµÑĢ

0.14

ãĥ©ãĤ¯

0.14

ãĥ«ãĥķ

0.14

Activations Density 0.039%

mentions of "first things" or significant initial actions in a narrative

No Comments

No Known Activations