INDEX

Explanations

specific phrases and discussions regarding concepts or events that are of interest or consideration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

¨

-0.14

alin

-0.14

ume

-0.14

oid

-0.14

banks

-0.13

local

-0.13

dem

-0.13

Uns

-0.13

ops

-0.13

POSITIVE LOGITS

ucer

0.15

pector

0.15

 thing

0.15

 Ð½ÐµÐ´ÐµÐ»

0.15

rowave

0.15

ukes

0.15

iten

0.15

±

0.14

gett

0.14

iked

0.14

Activations Density 0.415%

specific phrases and discussions regarding concepts or events that are of interest or consideration

No Comments

No Known Activations