INDEX

Explanations

occurrences of time-related phrases and historical references

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

 Verg

-0.15

aks

-0.15

jug

-0.14

YSTEM

-0.14

izer

-0.14

 Pearce

-0.13

way

-0.13

Cov

-0.13

 falls

-0.13

 earliest

-0.13

POSITIVE LOGITS

oron

0.16

olas

0.16

0.15

ryn

0.15

 Beacon

0.14

olis

0.14

legate

0.14

åºľ

0.14

ync

0.14

immer

0.14

Activations Density 0.020%

occurrences of time-related phrases and historical references

No Comments

No Known Activations